© 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. 53609
    Prev
    Next
    INDEX
    Explanations

    not that / one day / according to

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

    suggesting parts

    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
     стрем
    0.49
     để
    0.48
     в
    0.48
     на
    0.47
     лен
    0.45
     от
    0.44
     З
    0.44
     on
    0.43
     bogged
    0.43
     да
    0.43
    POSITIVE LOGITS
     रहिए
    0.46
    স্থানীয়
    0.45
    λευτα
    0.42
    PROTOCOL
    0.41
    স্বামী
    0.41
     biologiques
    0.41
    শাস্ত্র
    0.41
    세요
    0.40
    DJ
    0.40
    جراء
    0.40
    Activations Density 0.000%

    No Known Activations