© 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. 199711
    Prev
    Next
    INDEX
    Explanations

    relationships and control

    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
    staaten
    0.46
     অর্থে
    0.45
    អនុ
    0.45
    തിൽ
    0.45
     మంచి
    0.44
    লিখিত
    0.44
     النرويج
    0.44
    郴
    0.44
    ହି
    0.43
    береж
    0.43
    POSITIVE LOGITS
     sequence
    0.50
     rising
    0.50
     lower
    0.48
     plur
    0.48
     sequences
    0.46
     straining
    0.46
    underline
    0.44
     flamb
    0.44
     Yaman
    0.44
     crossing
    0.44
    Activations Density 0.003%

    No Known Activations