© 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. 136602
    Prev
    Next
    INDEX
    Explanations

    with others cannot

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

    attackers try

    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
    SEM
    0.58
    sem
    0.48
    legal
    0.46
    슷
    0.46
    ups
    0.45
    ataan
    0.44
    esm
    0.44
    ijer
    0.44
    foam
    0.44
     doorway
    0.43
    POSITIVE LOGITS
     narzęd
    0.50
     menacing
    0.45
    ツール
    0.44
    ZIONE
    0.44
    स्कूल
    0.43
     программи
    0.43
     technische
    0.42
    ஈ
    0.42
     இயக்கு
    0.41
    স্থানীয়
    0.41
    Activations Density 0.001%

    No Known Activations