© 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. 163330
    Prev
    Next
    INDEX
    Explanations

    hobbies prior no foam

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

    image, risk, credentials

    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
     Forests
    0.49
    at
    0.45
    S
    0.45
     ис
    0.45
     памя
    0.44
    with
    0.44
    ukul
    0.44
     बेसब्री
    0.43
     капитала
    0.43
    Tapi
    0.43
    POSITIVE LOGITS
    🆚
    0.48
    出现在
    0.46
    伪
    0.46
    )=\{
    0.46
    蚱
    0.46
    CHUNK
    0.44
    螫
    0.44
    ುವುದ
    0.43
    ────────
    0.43
    崩溃
    0.43
    Activations Density 0.000%

    No Known Activations