© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170063
    Prev
    Next
    INDEX
    Explanations

    length dress, racial origin, password, towns

    np_acts-logits-general · gemini-2.5-flash-lite

    concrete nouns and hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ве
    0.52
     therapist
    0.46
    <0xD0>
    0.43
     scegli
    0.43
    عرف
    0.42
     punya
    0.41
     therapists
    0.41
     типу
    0.41
    Це
    0.41
    দীন
    0.40
    POSITIVE LOGITS
    屇
    0.49
     सिया
    0.47
     concealment
    0.47
     στοι
    0.45
     calles
    0.44
     पाल
    0.44
    陖
    0.44
     რომელი
    0.43
     ते
    0.43
    一同
    0.43
    Activations Density 0.001%

    No Known Activations