© 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. 196073
    Prev
    Next
    INDEX
    Explanations

    sweaters, customized, service

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

    foreign and technical terms

    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
     refineries
    0.52
    O
    0.52
     electrification
    0.51
     meters
    0.50
     alpha
    0.49
     rhod
    0.47
    ERING
    0.46
     controllable
    0.46
     ALPHA
    0.46
    ্ধ
    0.45
    POSITIVE LOGITS
    voor
    0.52
    われる
    0.51
    getFullName
    0.51
     vremena
    0.49
    僮
    0.47
    われた
    0.46
    leistungen
    0.46
    uvad
    0.46
    verband
    0.45
    uldu
    0.45
    Activations Density 0.000%

    No Known Activations