© 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. 200072
    Prev
    Next
    INDEX
    Explanations

    content types and sales

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

    predicting subsequent words

    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
    콴
    0.46
    фу
    0.44
    цю
    0.43
    этому
    0.42
     كلمه
    0.42
    ເຄື່ອງ
    0.42
    يش
    0.41
    Acetoxy
    0.41
     요거
    0.41
    शीट
    0.41
    POSITIVE LOGITS
     (
    0.46
    ctors
    0.46
    giene
    0.45
     olid
    0.44
    arc
    0.44
    ကာ
    0.44
     appeals
    0.43
     gon
    0.43
    ators
    0.42
     கால
    0.42
    Activations Density 0.001%

    No Known Activations