© 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. 85951
    Prev
    Next
    INDEX
    Explanations

    exposure, voltage, N, V

    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
    饞
    0.64
     yöntem
    0.64
    出て
    0.60
     sécr
    0.60
     эм
    0.58
    },(
    0.57
    ออกมา
    0.57
    噰
    0.57
     jednym
    0.57
     nghĩ
    0.56
    POSITIVE LOGITS
    at
    0.63
    -
    0.57
    ur
    0.56
    _
    0.55
    mans
    0.51
    nections
    0.50
    rat
    0.49
    hmen
    0.49
    da
    0.48
    alas
    0.48
    Activations Density 0.000%

    No Known Activations