© 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-16K
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    disruption, disputed, disapproval

    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_16k_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
     emits
    0.31
    ("
    0.31
    tries
    0.29
     (%
    0.29
     WITH
    0.28
     selectable
    0.28
     +(
    0.28
    a
    0.27
     ("
    0.27
    ();
    0.26
    POSITIVE LOGITS
     기대
    0.24
    -
    0.24
    и
    0.24
    ings
    0.23
    데이트
    0.23
     социальных
    0.23
    خواه
    0.23
    难
    0.23
    сты
    0.22
     expectativas
    0.22
    Activations Density 0.055%

    No Known Activations