© 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. 9987
    Prev
    Next
    INDEX
    Explanations

    brakes, tiber, mat, amidst

    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
     Linux
    0.48
    Linux
    0.47
    基金
    0.44
    S
    0.44
    RY
    0.42
     ransomware
    0.42
     Huawei
    0.42
     resveratrol
    0.41
     virtualization
    0.41
     stoichiometry
    0.41
    POSITIVE LOGITS
    onnées
    0.58
    adă
    0.55
    bounded
    0.54
     éd
    0.54
    ylle
    0.52
    agée
    0.52
    depart
    0.51
    ٧
    0.51
     изда
    0.51
    väl
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.