© 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. 104580
    Prev
    Next
    INDEX
    Explanations

    tennis, children, or leisure activities

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

    water pushing

    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
    ९
    0.55
    durationType
    0.53
    ]$
    0.50
     এইরূপে
    0.48
    年后
    0.46
     numberWith
    0.46
    ρω
    0.46
     później
    0.46
    岃
    0.46
    ‌ترین
    0.44
    POSITIVE LOGITS
     Aktual
    0.42
     I
    0.41
     Bios
    0.41
    nect
    0.40
     Intell
    0.40
    icillin
    0.40
     NCR
    0.39
     Fc
    0.39
     vetro
    0.39
     παρέ
    0.39
    Activations Density 0.000%

    No Known Activations