© 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. 17628
    Prev
    Next
    INDEX
    Explanations

    increasingly common, popular, critical

    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
    し
    1.34
    وم
    1.16
    ]，
    1.10
    】，
    1.09
    ون
    1.05
    ]。
    1.02
    드
    1.01
    کس
    1.00
    %。
    1.00
    》。
    0.96
    POSITIVE LOGITS
    .
    0.93
    u
    0.91
     on
    0.91
    t
    0.90
    s
    0.89
    on
    0.86
    ,
    0.82
     Spring
    0.82
    al
    0.80
     Get
    0.79
    Activations Density 0.060%

    No Known Activations