© 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. 145101
    Prev
    Next
    INDEX
    Explanations

    applicable

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

    language models or concepts

    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
     rebellious
    0.50
     distilled
    0.49
     distiller
    0.47
     speedometer
    0.46
     straighten
    0.46
    氶
    0.45
    زاء
    0.45
     oppressive
    0.45
     impro
    0.44
     distillation
    0.44
    POSITIVE LOGITS
    குறி
    0.54
     빅
    0.49
    องค์การ
    0.48
    スメ
    0.45
    "$
    0.44
    exists
    0.44
     ঠিক
    0.43
     зда
    0.43
    빅
    0.43
    Update
    0.43
    Activations Density 0.000%

    No Known Activations