© 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. 31-GEMMASCOPE-2-RES-262K
    7. 123797
    Prev
    Next
    INDEX
    Explanations

    zero-shot learning

    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_31_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
     kész
    0.45
     inflater
    0.43
    笛
    0.42
    >
    0.41
     contribut
    0.41
    ubin
    0.41
    >{{
    0.41
     Blogging
    0.41
    ဖ
    0.40
    luft
    0.40
    POSITIVE LOGITS
    out
    0.48
    או
    0.46
     notion
    0.45
     یعنی
    0.45
     طریقے
    0.44
    ...)
    0.44
     ولی
    0.42
    evaluation
    0.42
    Transpose
    0.42
    ainty
    0.42
    Activations Density 0.006%

    No Known Activations