© 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. 11616
    Prev
    Next
    INDEX
    Explanations

    causing an effect

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

    produces an outcome

    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
    llium
    0.41
    unky
    0.41
     Ме
    0.40
     英
    0.40
    stätte
    0.38
    असल
    0.38
    焖
    0.37
    itect
    0.37
    actic
    0.37
     Ба
    0.37
    POSITIVE LOGITS
     overlap
    0.43
     edgecolor
    0.42
    比
    0.42
     adata
    0.42
     misma
    0.41
     aliquot
    0.40
     valoración
    0.40
     respect
    0.40
     amplitud
    0.40
    ஸின்
    0.39
    Activations Density 0.000%

    No Known Activations