© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 166764
    Prev
    Next
    INDEX
    Explanations

    between words, ideas, parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vv
    0.39
    biggl
    0.37
    "%(
    0.37
    CBUUID
    0.36
    ങ്ങ
    0.36
    VV
    0.36
    维度
    0.35
    ierung
    0.35
     ದಿನ
    0.35
    geordnet
    0.35
    POSITIVE LOGITS
     scones
    0.43
    ሱን
    0.41
    ጄ
    0.39
     crackers
    0.39
     Alec
    0.38
     Travel
    0.38
     lockdown
    0.38
     TRAVEL
    0.38
    觧
    0.38
     travel
    0.37
    Activations Density 0.003%

    No Known Activations