© 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. 152522
    Prev
    Next
    INDEX
    Explanations

    job term monthly report

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

    modules, environments, presence

    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
    QTTR
    0.49
     vuonna
    0.47
     परवानगी
    0.46
    本身的
    0.45
     ট্যাবলেট
    0.44
    Ə
    0.43
    oraus
    0.42
    라는
    0.42
     信息
    0.42
     室
    0.42
    POSITIVE LOGITS
    𝕖
    0.59
    ς
    0.49
     accomplishes
    0.48
     ব্যা
    0.47
    e
    0.47
    انه
    0.46
     выполняется
    0.46
    та
    0.46
    飏
    0.45
     Kane
    0.45
    Activations Density 0.000%

    No Known Activations