© 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. 150549
    Prev
    Next
    INDEX
    Explanations

    struggles socially, calf quickly, happens to

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

    foreign words

    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
     type
    0.46
    Type
    0.44
     τύ
    0.43
     loses
    0.43
     Immutable
    0.43
     मैंने
    0.42
     돼
    0.42
     타입
    0.41
     and
    0.41
    cas
    0.41
    POSITIVE LOGITS
    চাই
    0.53
     sacerdote
    0.52
    ாரு
    0.51
    ياء
    0.50
    祟
    0.50
    વેશ
    0.50
     verfügbar
    0.50
     año
    0.49
    矚
    0.48
    講演
    0.48
    Activations Density 0.000%

    No Known Activations