© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    class properties and methods

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

    class constructors

    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
     pédicule
    0.49
    Campbell
    0.48
    gleichen
    0.45
    einander
    0.44
    ना
    0.44
     விழுப்பு
    0.43
    Denovo
    0.43
    營
    0.42
    淹
    0.42
     vết
    0.42
    POSITIVE LOGITS
     constructor
    0.71
    constructor
    0.62
     Constructor
    0.59
     __
    0.55
     initialize
    0.54
     hold
    0.53
     readonly
    0.52
     Attributes
    0.51
     owns
    0.50
     own
    0.49
    Activations Density 0.000%

    No Known Activations