© 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. 137007
    Prev
    Next
    INDEX
    Explanations

    Greek pattern

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

    dopamine, brain, success

    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
     总
    0.47
    ้าน
    0.47
     ARR
    0.46
     articulate
    0.46
     夜
    0.45
     inhab
    0.45
    萌
    0.44
    ราว
    0.44
    铠
    0.44
     斜
    0.43
    POSITIVE LOGITS
    impurity
    0.57
    engo
    0.54
    edly
    0.50
    entery
    0.46
    abilit
    0.46
    ability
    0.45
    ession
    0.45
    ἐ
    0.44
    injury
    0.44
    قف
    0.44
    Activations Density 0.000%

    No Known Activations