© 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. 52845
    Prev
    Next
    INDEX
    Explanations

    handles missing data

    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
    ABILITY
    0.56
     fulfils
    0.48
    LOCK
    0.47
     a
    0.46
    Che
    0.44
    ший
    0.44
     subarrays
    0.43
     playerCards
    0.43
    ﺵ
    0.42
    GER
    0.41
    POSITIVE LOGITS
    ائیگی
    0.46
    éct
    0.44
     टक
    0.43
    guồn
    0.42
     继续
    0.42
    calaureate
    0.42
     كيف
    0.40
    olve
    0.40
     rulemaking
    0.40
     crook
    0.40
    Activations Density 0.005%

    No Known Activations