© 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. 143618
    Prev
    Next
    INDEX
    Explanations

    place names and locations

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

    protobuf, actually, communist, rule, direction, organized

    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
    PROTE
    0.47
    轉
    0.46
     footh
    0.46
    HARD
    0.46
    MASTER
    0.45
     regain
    0.43
     voltam
    0.43
     fueron
    0.42
    ECUT
    0.42
    SINGLE
    0.42
    POSITIVE LOGITS
    ään
    0.50
    ären
    0.48
    ğın
    0.46
    *,
    0.46
    essive
    0.46
    *(
    0.45
    Ordinal
    0.45
    żs
    0.44
    𝓲
    0.44
    inference
    0.44
    Activations Density 0.001%

    No Known Activations