© 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. 115547
    Prev
    Next
    INDEX
    Explanations

    course - pixel and ideas

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

    clarify specific context

    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
    0.53
     تباہ
    0.48
     stvar
    0.47
     treinta
    0.43
    𝚆
    0.43
    処理
    0.43
     jist
    0.43
    <0xA6>
    0.42
    acial
    0.42
    <0xB4>
    0.42
    POSITIVE LOGITS
    藻
    0.46
     ấy
    0.45
    ش
    0.45
    诸
    0.45
    poi
    0.43
    lą
    0.43
    சாலை
    0.43
    மான்
    0.42
    menos
    0.41
     Takah
    0.41
    Activations Density 0.000%

    No Known Activations