© 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. 8411
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful content

    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
    w
    1.01
    t
    0.93
    ก
    0.91
    '
    0.87
    ized
    0.83
    n
    0.82
    g
    0.80
     wan
    0.76
     investir
    0.76
    nard
    0.75
    POSITIVE LOGITS
    as
    1.24
    ARE
    1.18
     refusal
    1.18
    R
    1.14
    are
    1.13
    P
    1.07
    9
    1.05
    AS
    1.02
    S
    1.00
    el
    0.97
    Activations Density 0.020%

    No Known Activations