© 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. 95947
    Prev
    Next
    INDEX
    Explanations

    conditional or movie related

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

    limited resources or constraints

    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
    Q
    0.55
    U
    0.54
    XK
    0.52
    ER
    0.52
    UK
    0.51
    شی
    0.50
    K
    0.50
    Cm
    0.49
    Eb
    0.48
     -
    0.48
    POSITIVE LOGITS
     那麼
    0.55
    itre
    0.52
    mato
    0.51
     Тому
    0.50
     calcareous
    0.49
     తెలియ
    0.49
    啞
    0.48
    譯
    0.48
    нике
    0.47
    餚
    0.47
    Activations Density 0.000%

    No Known Activations