© 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. 29897
    Prev
    Next
    INDEX
    Explanations

    sizes fit, surface navy, main categories

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

    quantization, ML, common words

    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
    K
    0.50
    Terry
    0.49
    イッチ
    0.47
     sami
    0.46
     comrades
    0.43
    鐸
    0.43
    Klas
    0.43
     individu
    0.43
    Guild
    0.43
    Adi
    0.43
    POSITIVE LOGITS
    avourable
    0.49
    avorable
    0.47
     சூழ்
    0.46
    tų
    0.45
     반드시
    0.44
    💊
    0.43
    ^*_{
    0.43
    methods
    0.42
    maması
    0.42
    ález
    0.42
    Activations Density 0.000%

    No Known Activations