© 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. 92062
    Prev
    Next
    INDEX
    Explanations

    which of the following

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

    which of the following

    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
    Identify
    0.49
    identify
    0.47
     whose
    0.44
     _______
    0.44
     ______
    0.44
    GetAsyncKeyState
    0.44
     ambayo
    0.44
     Identify
    0.43
     _____
    0.43
    simplify
    0.42
    POSITIVE LOGITS
    以下
    0.55
    以下的
    0.52
    下記
    0.49
     folgenden
    0.48
    ofthe
    0.45
     of
    0.43
     folgender
    0.43
     one
    0.42
    如下
    0.42
    下面的
    0.41
    Activations Density 0.002%

    No Known Activations