© 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. 44368
    Prev
    Next
    INDEX
    Explanations

    private sub or const min

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

    public function

    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
     Apartments
    0.48
    formerly
    0.46
     Nucleaires
    0.46
     এখানকার
    0.46
     Pole
    0.45
    阔
    0.45
     লই
    0.45
    ဖြစ်သည်။
    0.45
    んじゃない
    0.44
    ρης
    0.44
    POSITIVE LOGITS
     to
    0.55
     pog
    0.52
     mesaj
    0.50
     sesi
    0.47
     jat
    0.46
     rethink
    0.46
     oba
    0.45
     collaborate
    0.45
     조
    0.44
     exodus
    0.44
    Activations Density 0.000%

    No Known Activations