© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3731
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

    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_16_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
    ronique
    0.45
    ння
    0.44
    nich
    0.42
    🚮
    0.42
    รือ
    0.41
    totime
    0.41
    ่
    0.41
    orno
    0.41
    🍘
    0.41
     incentiv
    0.39
    POSITIVE LOGITS
    for
    0.57
     for
    0.55
    in
    0.49
    the
    0.46
    ７
    0.46
    of
    0.45
    is
    0.44
    THE
    0.43
    T
    0.41
    两
    0.40
    Activations Density 0.179%

    No Known Activations