© 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. 143123
    Prev
    Next
    INDEX
    Explanations

    travel and insurances

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

    data type conversion conversions

    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
     Epoxy
    0.44
     diameter
    0.43
     $(
    0.42
     $\%$
    0.42
     validated
    0.41
     dank
    0.41
     $=
    0.40
    laşt
    0.40
    לית
    0.40
     $\{\
    0.40
    POSITIVE LOGITS
    _->
    0.50
    ussch
    0.46
    cF
    0.45
    Relation
    0.44
    協力
    0.43
     جلوگیری
    0.43
     autrefois
    0.42
    }.",
    0.42
    Provider
    0.42
     বাঙ্গালীর
    0.42
    Activations Density 0.000%

    No Known Activations