© 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. 196471
    Prev
    Next
    INDEX
    Explanations

    prospective business

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

    urban areas

    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
     существу
    0.50
    ើង
    0.48
     стены
    0.48
     звер
    0.47
    ャ
    0.46
     스타일
    0.46
     труд
    0.46
     ఉన్నాయి
    0.45
     είναι
    0.45
     пород
    0.45
    POSITIVE LOGITS
    اللہ
    0.49
     degli
    0.45
    cing
    0.45
    ò
    0.45
    机关
    0.45
    лій
    0.44
    ul
    0.43
    litz
    0.43
    orgen
    0.42
    ~)
    0.42
    Activations Density 0.000%

    No Known Activations