© 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. 51217
    Prev
    Next
    INDEX
    Explanations

    specific details after introductory phrases

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

    ride out, crucial, shape, read, Education, holding

    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
    圖
    0.49
    ਵ
    0.48
    数値
    0.48
    세
    0.47
    PLANE
    0.46
    CENTER
    0.46
    ਪ
    0.46
    TYPES
    0.45
     शत
    0.45
    積
    0.45
    POSITIVE LOGITS
     acudir
    0.46
     lei
    0.44
     ue
    0.44
     mousse
    0.43
    inizin
    0.43
     kayaking
    0.42
     Chaos
    0.42
     sauerkraut
    0.42
     ferry
    0.42
     leaching
    0.42
    Activations Density 0.000%

    No Known Activations