© 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. 52835
    Prev
    Next
    INDEX
    Explanations

    family matters

    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
    dale
    0.47
    occurrence
    0.46
    represented
    0.44
    uli
    0.43
    tor
    0.42
    ost
    0.41
    ded
    0.41
    ,
    0.41
    abic
    0.41
    inst
    0.40
    POSITIVE LOGITS
     vetting
    0.55
     vetted
    0.54
     critters
    0.52
     hurdle
    0.49
     bạn
    0.48
     mung
    0.48
     এটাও
    0.47
    你要
    0.46
     quieres
    0.46
     champs
    0.45
    Activations Density 0.013%

    No Known Activations