© 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. 36926
    Prev
    Next
    INDEX
    Explanations

    phrases after common words

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

    formatting and specific terms

    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
    संग
    0.58
    EN
    0.54
    𒈨
    0.53
    𝟭
    0.51
    今天
    0.50
    ให้บริการ
    0.49
    在
    0.49
     últimos
    0.48
    ו
    0.48
    螫
    0.48
    POSITIVE LOGITS
    ↵
    0.59
     baskets
    0.53
     barrel
    0.51
     barrels
    0.50
    '
    0.49
     hill
    0.49
     tobacco
    0.47
     Tatra
    0.47
     nieces
    0.47
     movie
    0.46
    Activations Density 0.000%

    No Known Activations