Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13076
    Prev
    Next
    INDEX
    Explanations

    lists of terms and descriptions

    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
    /),
    0.39
    ).</
    0.38
    `),
    0.38
     crad
    0.38
    ”),
    0.37
    ”).
    0.37
     %),
    0.36
     emphas
    0.36
    ."),
    0.36
    ங்கிய
    0.36
    POSITIVE LOGITS
    </h2>
    0.59
    </h3>
    0.54
    </h4>
    0.54
    ?
    0.52
    怎么办
    0.51
    ؟
    0.51
    :
    0.48
    !
    0.47
    ?
    0.46
    ↵↵
    0.45
    Activations Density 0.438%

    No Known Activations