© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32849
    Prev
    Next
    INDEX
    Explanations

    will comeFor morewho entrustif theyprobably wonat leastcontacted thestrong indicatoras provided. will comeFor morewho entrustif theyprobably wonat leastcontacted thestrong indicatoras provided

    np_acts-logits-general · gemini-2.5-flash-lite

    ability needs capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stitute
    0.46
    이
    0.45
     lined
    0.44
    画像の
    0.44
     조금
    0.44
    보고
    0.43
    ﾐ
    0.43
     केवल
    0.42
    廸
    0.42
    पाल
    0.41
    POSITIVE LOGITS
     Prin
    0.45
     Print
    0.43
     Pier
    0.43
    Cuánt
    0.42
     Schritte
    0.42
     Bü
    0.42
     Deut
    0.41
     Neuer
    0.41
     Hinter
    0.41
     Grü
    0.41
    Activations Density 0.000%

    No Known Activations