© 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. 109882
    Prev
    Next
    INDEX
    Explanations

    search queries

    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
    ాం
    0.55
    罾
    0.54
     Pix
    0.52
    jami
    0.50
     Drexel
    0.49
     Jér
    0.49
    醀
    0.49
    喜剧
    0.47
     piek
    0.46
    joni
    0.46
    POSITIVE LOGITS
    as
    0.61
     sustains
    0.54
    ina
    0.54
    :=
    0.53
    conscious
    0.52
    coherent
    0.51
    csak
    0.51
    te
    0.51
    =
    0.51
    burning
    0.50
    Activations Density 0.000%

    No Known Activations