© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 199197
    Prev
    Next
    INDEX
    Explanations

    provide information or actions

    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
     invariant
    0.52
    m
    0.52
    loan
    0.52
    MAN
    0.49
    ma
    0.48
    lt
    0.48
    NA
    0.48
    u
    0.48
    g
    0.48
    kl
    0.46
    POSITIVE LOGITS
    Choisissez
    0.52
     કરો
    0.49
    ேஷ்
    0.49
    тся
    0.48
    ності
    0.48
    ುದ
    0.47
    ться
    0.46
     ይች
    0.45
     થયો
    0.45
     стороны
    0.45
    Activations Density 0.002%

    No Known Activations