© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91896
    Prev
    Next
    INDEX
    Explanations

    reduce aggression or positively influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeerItem
    0.50
    İ
    0.50
    üm
    0.48
     прадстаў
    0.47
     představ
    0.47
    кри
    0.45
    ۹
    0.45
    Harm
    0.45
    冦
    0.45
    瑆
    0.45
    POSITIVE LOGITS
     congregations
    0.49
     Scotch
    0.48
     cemeteries
    0.45
     groves
    0.44
     community
    0.43
     |\
    0.43
     congruence
    0.43
     urban
    0.42
     charities
    0.41
     crevices
    0.41
    Activations Density 0.005%

    No Known Activations