© 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. 68670
    Prev
    Next
    INDEX
    Explanations

    unique items or people

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

    following 'below'

    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
    ❒
    0.48
     IEnumerable
    0.47
     ArrayRef
    0.46
     quiser
    0.44
     quis
    0.43
    Integer
    0.42
    窰
    0.42
    leet
    0.42
    倍
    0.42
     oldal
    0.41
    POSITIVE LOGITS
    criterion
    0.48
    letter
    0.45
    scene
    0.44
     Genoa
    0.43
    শিপ
    0.43
    FUENTE
    0.43
    ಬಿ
    0.42
     vivos
    0.42
    specification
    0.42
    éra
    0.41
    Activations Density 0.000%

    No Known Activations