© 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. 127925
    Prev
    Next
    INDEX
    Explanations

    included, A, some, up, will

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

    deliberately stripping

    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
    <unused2148>
    0.54
     sondern
    0.53
     leftist
    0.52
     scoff
    0.52
     Deshalb
    0.49
    ństwo
    0.47
     griev
    0.46
     deshalb
    0.45
     drž
    0.45
     deswegen
    0.45
    POSITIVE LOGITS
    检索
    0.52
    时不
    0.51
    砼
    0.50
    这个
    0.47
    没什么
    0.47
    关节
    0.47
    에도
    0.47
    ไม่
    0.46
     diagnostics
    0.46
    厕
    0.46
    Activations Density 0.005%

    No Known Activations