© 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. 106030
    Prev
    Next
    INDEX
    Explanations

    locator, what, whoever, promises

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

    universities, future outcomes, constraints

    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
    由于
    0.54
    ాల్సిన
    0.46
    明确
    0.46
     cần
    0.45
     került
    0.45
    丧
    0.43
    确定
    0.42
    确认
    0.41
     потребуется
    0.41
    关于
    0.40
    POSITIVE LOGITS
     humanist
    0.50
     次元
    0.49
     katal
    0.48
     cataly
    0.47
    gger
    0.46
    leg
    0.46
    instant
    0.46
    ror
    0.45
    energia
    0.45
    isolation
    0.45
    Activations Density 0.001%

    No Known Activations