© 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. 217829
    Prev
    Next
    INDEX
    Explanations

    words following suffixes

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

    foundation and organization

    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
     há
    0.53
     crafted
    0.51
     Detroit
    0.49
     harassed
    0.48
     bargaining
    0.48
    毓
    0.47
     coaches
    0.46
     harassment
    0.46
     حاضر
    0.45
     tá
    0.45
    POSITIVE LOGITS
    It
    0.53
    Elle
    0.52
    Angleterre
    0.52
    ان
    0.50
    unile
    0.48
    </
    0.48
    Lors
    0.47
    나가
    0.47
    ANGER
    0.47
    urile
    0.46
    Activations Density 0.001%

    No Known Activations