© 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. 173583
    Prev
    Next
    INDEX
    Explanations

    technical and informational terms

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

    explanation of policies

    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
    短暂
    0.45
    ló
    0.44
    下列
    0.42
    间
    0.41
    floating
    0.41
    のではない
    0.41
    docker
    0.40
     maybe
    0.40
    maybe
    0.40
    is
    0.40
    POSITIVE LOGITS
     전국
    0.57
     فیصد
    0.54
     बरकरार
    0.52
     вол
    0.48
     героев
    0.47
     تمام
    0.47
     घटकर
    0.47
    ቷ
    0.46
     aggior
    0.46
     Воло
    0.46
    Activations Density 0.000%

    No Known Activations