© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205030
    Prev
    Next
    INDEX
    Explanations

    file descriptors 0 1 2

    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_40_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
    綬
    0.43
     SS
    0.39
     sockaddr
    0.39
    strftime
    0.38
    killing
    0.38
    descriptor
    0.38
     strerror
    0.38
     comunidades
    0.37
    ütt
    0.37
    風味
    0.37
    POSITIVE LOGITS
     automatic
    0.46
     Automatic
    0.45
     automático
    0.45
     poetic
    0.43
    Automatic
    0.42
     Compaq
    0.41
     >=
    0.41
    ரத்தில்
    0.40
     higher
    0.38
     wizard
    0.38
    Activations Density 0.006%

    No Known Activations