© 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. 210169
    Prev
    Next
    INDEX
    Explanations

    Elvis and James Brown

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

    儒学

    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
    গোষ্ঠ
    0.60
    grove
    0.49
     আওয়
    0.46
    াসের
    0.46
     \%
    0.45
    varchar
    0.45
    एमसी
    0.45
    ទទួលបាន
    0.45
    сколько
    0.44
     excitatory
    0.44
    POSITIVE LOGITS
    ia
    0.51
    }}:
    0.49
    ug
    0.48
     شك
    0.46
    嚗
    0.45
    ك
    0.44
    ain
    0.43
    ugu
    0.43
     लगाएं
    0.42
    忝
    0.42
    Activations Density 0.000%

    No Known Activations