© 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. 123180
    Prev
    Next
    INDEX
    Explanations

    specific descriptive phrases

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

    style purpose bits elements

    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
    uid
    0.50
    (
    0.47
    4
    0.46
    assay
    0.45
    auxite
    0.44
    :
    0.44
    aks
    0.43
    athy
    0.43
    ant
    0.43
    extraction
    0.43
    POSITIVE LOGITS
    אר
    0.55
    前来
    0.51
     profitieren
    0.51
     ö
    0.51
    楦
    0.50
     toz
    0.50
    用于
    0.48
     đọc
    0.48
     මත
    0.48
     przyj
    0.47
    Activations Density 0.001%

    No Known Activations