© 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. 63784
    Prev
    Next
    INDEX
    Explanations

    stalactites and stalagmites

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

    describing incidents and issues

    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
    <0x15>
    0.45
    2
    0.44
    std
    0.43
    ต้อง
    0.43
    )”.
    0.42
    他に
    0.42
    ashita
    0.42
     продолжа
    0.41
    必須
    0.41
    👦
    0.41
    POSITIVE LOGITS
     presto
    0.45
     části
    0.45
     hobbies
    0.45
     Albion
    0.44
     Currie
    0.44
    χη
    0.43
     nerada
    0.43
     cuándo
    0.43
     товара
    0.43
     Rond
    0.43
    Activations Density 0.000%

    No Known Activations