© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108199
    Prev
    Next
    INDEX
    Explanations

    name variations like Cara, Cari

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

    community property

    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
    Negative Logits
     परिवर्तित
    0.54
    amily
    0.51
    ここに
    0.47
     temprana
    0.47
     तुम्
    0.46
    स्थापन
    0.45
    餓
    0.44
    otre
    0.44
     चाचा
    0.44
    ስታ
    0.44
    POSITIVE LOGITS
     mittens
    0.42
     zá
    0.42
     sneaky
    0.41
     ½
    0.41
    t
    0.41
     smiles
    0.40
    ेंजर
    0.40
    śmy
    0.40
     outgoing
    0.39
    šina
    0.38
    Activations Density 0.002%

    No Known Activations