© 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. 153513
    Prev
    Next
    INDEX
    Explanations

    random, assurances, Haiti, blood, eggs

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

    instructions or rules

    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
    localVarHTTP
    0.42
    🚋
    0.42
    npmjs
    0.40
    documents
    0.39
    уд
    0.39
    🍸
    0.39
     doubtless
    0.38
    Ы
    0.38
    OTHER
    0.38
     postérieures
    0.38
    POSITIVE LOGITS
     Indust
    0.57
     Instruction
    0.51
     Religion
    0.50
     Rand
    0.48
    ృష్ణ
    0.48
     Relig
    0.46
     Zeitschrift
    0.45
    坸
    0.45
     Uno
    0.44
     regression
    0.44
    Activations Density 0.001%

    No Known Activations