© 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. 43154
    Prev
    Next
    INDEX
    Explanations

    CDA Credential

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

    archetype and mined

    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
     همچنین
    0.45
     berth
    0.43
     вследствие
    0.43
     ক্ষত্রিয়
    0.42
    वें
    0.42
     さらに
    0.40
     chemokine
    0.40
    ໂ
    0.40
    以下の
    0.39
    Islamic
    0.39
    POSITIVE LOGITS
     spun
    0.44
     Three
    0.43
     Trois
    0.41
     ምንም
    0.41
     ढाई
    0.41
     dearly
    0.40
     Peyton
    0.39
     auraient
    0.39
     vivid
    0.39
     manh
    0.39
    Activations Density 0.000%

    No Known Activations