© 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. 162792
    Prev
    Next
    INDEX
    Explanations

    as they are

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

    trying to see substantial growth

    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
     脱
    0.53
     داد
    0.46
     Eighteenth
    0.46
     Çalış
    0.45
    <unused981>
    0.45
     comandante
    0.44
    脱
    0.44
     కానీ
    0.44
     husband
    0.43
    -【
    0.42
    POSITIVE LOGITS
    ígen
    0.49
     публі
    0.48
    geke
    0.46
     pickups
    0.46
    가를
    0.45
    igheden
    0.45
    임을
    0.45
    ólogos
    0.45
     периода
    0.45
     vyn
    0.44
    Activations Density 0.001%

    No Known Activations