© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130381
    Prev
    Next
    INDEX
    Explanations

    sensor, automatically, keypad, borough, burner

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

    installing software or choices

    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
    Negative Logits
    ۲۰
    0.47
     pà
    0.44
    INION
    0.43
     ја
    0.43
    Ώ
    0.43
     подро
    0.43
    Ironically
    0.43
     COMMUNICATIONS
    0.43
    チーム
    0.43
     ensayo
    0.42
    POSITIVE LOGITS
    沐
    0.49
    il
    0.47
    cru
    0.44
    cup
    0.43
    atibus
    0.43
    enderita
    0.42
    睑
    0.42
    ifices
    0.42
    leValue
    0.41
    aser
    0.40
    Activations Density 0.001%

    No Known Activations