© 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. 38384
    Prev
    Next
    INDEX
    Explanations

    defining dimensions and statements

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

    field origin, number, string, directional, time, story

    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
    yeah
    0.44
    وري
    0.41
    átil
    0.41
    waitForIdleSync
    0.40
     सेवाएं
    0.38
    淌
    0.38
    ciende
    0.38
     регулярно
    0.38
    iese
    0.38
     Gemeinde
    0.38
    POSITIVE LOGITS
    を作成
    0.46
    WF
    0.46
    三个
    0.44
     إنشاء
    0.44
    첫
    0.42
    𝗠
    0.42
    Statement
    0.42
     двой
    0.42
    稆
    0.42
    四个
    0.41
    Activations Density 0.000%

    No Known Activations