© 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. 102252
    Prev
    Next
    INDEX
    Explanations

    quantity, reward, requested, feel, thing, only, release

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

    Here's why

    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
    FileChooser
    0.45
    这个
    0.45
     这个
    0.44
    λυ
    0.43
    symplectic
    0.43
    了这个
    0.41
     এটাকে
    0.41
    树
    0.41
    šao
    0.41
    intos
    0.41
    POSITIVE LOGITS
     by
    0.46
     Kyl
    0.45
     परिस्थितियों
    0.44
     இருப்பினும்
    0.43
     signes
    0.43
     Abh
    0.42
     pasti
    0.42
     surpasses
    0.42
     времена
    0.42
     Kri
    0.41
    Activations Density 0.002%

    No Known Activations