© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45585
    Prev
    Next
    INDEX
    Explanations

    score and points

    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_65k_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
    на
    0.66
    ა
    0.61
    та
    0.61
    я
    0.61
    PPAR
    0.60
    ോ
    0.60
    ಿಗ
    0.59
    س
    0.59
    ко
    0.57
    ка
    0.57
    POSITIVE LOGITS
     scored
    0.99
     scores
    0.95
    Score
    0.95
    scores
    0.93
     score
    0.90
     Score
    0.86
    score
    0.81
    scoring
    0.81
     Scores
    0.80
     scoring
    0.80
    Activations Density 0.027%

    No Known Activations