© 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. 153648
    Prev
    Next
    INDEX
    Explanations

    attempted our best

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

    casualty, fear, or departure

    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
    Wallet
    0.51
    Upload
    0.50
    Average
    0.48
    Jpa
    0.46
    orderDetails
    0.45
    Tw
    0.45
    %-
    0.45
    rollerskates
    0.44
    Num
    0.44
    %,
    0.44
    POSITIVE LOGITS
     be
    0.58
     pear
    0.52
    '
    0.51
     deel
    0.47
     Pear
    0.47
     Casualty
    0.46
     accordance
    0.46
     cle
    0.46
     rhy
    0.46
     sac
    0.46
    Activations Density 0.001%

    No Known Activations