© 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. 42209
    Prev
    Next
    INDEX
    Explanations

    approved by, many fitness, after narrated, loud sound

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

    identifying problems or negative states

    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
    ed
    0.55
     endDate
    0.48
    畋
    0.44
    s
    0.44
     Function
    0.43
    1
    0.42
    ing
    0.42
     Source
    0.42
     Secondary
    0.42
    ⴻ
    0.41
    POSITIVE LOGITS
    حصل
    0.51
    UILLER
    0.46
    //////
    0.46
    ODO
    0.45
     갑
    0.45
    KM
    0.44
    ждении
    0.44
     đột
    0.44
     Наде
    0.44
     bashing
    0.44
    Activations Density 0.000%

    No Known Activations