© 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. 66287
    Prev
    Next
    INDEX
    Explanations

    ; then are cars of fault were trash

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

    breakdown of sections

    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
    اقی
    0.56
    주시
    0.51
    لیس
    0.50
    当
    0.49
    ική
    0.49
    目
    0.49
    壶
    0.49
    𝓟
    0.49
     teorías
    0.47
    轿
    0.47
    POSITIVE LOGITS
    osta
    0.54
    vee
    0.47
    ́
    0.46
    ie
    0.44
    vers
    0.43
    il
    0.43
    eg
    0.43
     ermög
    0.42
    glial
    0.42
    fi
    0.41
    Activations Density 0.000%

    No Known Activations