© 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. 28622
    Prev
    Next
    INDEX
    Explanations

    step, route, tip, reason

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

    numbered steps and approaches

    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
    cyclic
    0.49
    \%,
    0.49
    if
    0.47
    on
    0.47
    reti
    0.46
    agence
    0.45
    `
    0.44
    gcc
    0.44
    )},
    0.44
    ្នុង
    0.44
    POSITIVE LOGITS
     просмотра
    0.48
     روا
    0.46
     திருக்கோ
    0.45
     น้ำ
    0.44
     Ле
    0.43
     Katie
    0.43
    观看
    0.43
     العنوان
    0.42
     Crystal
    0.42
     Богу
    0.42
    Activations Density 0.000%

    No Known Activations