© 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. 32896
    Prev
    Next
    INDEX
    Explanations

    installation and setup steps

    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
    é
    0.55
    Cada
    0.48
     subtypes
    0.47
    Active
    0.47
    ş
    0.46
    ke
    0.45
    éz
    0.45
    us
    0.44
    St
    0.44
    levels
    0.44
    POSITIVE LOGITS
    安裝
    0.49
    ափ
    0.45
    полнение
    0.44
     INSTALL
    0.44
    脈
    0.42
     началь
    0.42
     tch
    0.42
    興
    0.42
    في
    0.41
     Lowest
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.