© 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. 104259
    Prev
    Next
    INDEX
    Explanations

    impact on operation

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

    private saving

    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
    も
    0.49
     colonial
    0.47
     prodigious
    0.46
     credible
    0.45
     torsion
    0.44
     industri
    0.44
     protos
    0.44
     solide
    0.44
    도
    0.43
     caries
    0.43
    POSITIVE LOGITS
     സൃ
    0.57
     αριθ
    0.57
    getContext
    0.52
     operandSize
    0.51
    Ẵ
    0.50
     সঠিকভাবে
    0.49
    滤
    0.49
     সংখ্যাগ
    0.48
     Adrián
    0.48
    徇
    0.48
    Activations Density 0.001%

    No Known Activations