© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    ruin, destroy, spoil

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

    ruin reputation relationships health

    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
    is
    0.40
    expression
    0.39
    are
    0.38
    event
    0.38
    on
    0.38
     \
    0.38
    i
    0.38
    os
    0.36
    returns
    0.36
    eas
    0.36
    POSITIVE LOGITS
     ruining
    0.75
     ruin
    0.75
     ruins
    0.71
     ruined
    0.67
     irrepar
    0.61
     havoc
    0.59
     destroys
    0.56
     irreparable
    0.53
     разру
    0.51
     बरबाद
    0.51
    Activations Density 0.093%

    No Known Activations