© 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. 125940
    Prev
    Next
    INDEX
    Explanations

    specific terms and conditions

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

    forward pass

    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
     äußerst
    0.43
     сверху
    0.40
    ૯
    0.40
    ७
    0.39
    ８
    0.39
    ２
    0.39
    ๒
    0.38
    Einzel
    0.38
    𝐧
    0.38
    ※
    0.38
    POSITIVE LOGITS
     for
    0.46
     havia
    0.42
     tentando
    0.41
     Harvard
    0.38
     For
    0.38
     avevano
    0.38
     fizeram
    0.37
     McDonalds
    0.37
     FAQ
    0.37
     legislation
    0.36
    Activations Density 0.093%

    No Known Activations