© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2177
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     spelled
    0.74
    <%=
    0.65
     %[
    0.65
     अवगत
    0.64
    }.",
    0.62
     व
    0.61
     addressed
    0.61
     —¿
    0.60
     потенциа
    0.60
     unprocessed
    0.59
    POSITIVE LOGITS
    </bbox>
    0.87
    rbrakk
    0.80
     )
    0.79
     ))
    0.79
     )))
    0.76
    endif
    0.76
     endif
    0.74
    </thead>
    0.73
    zetek
    0.73
     ),
    0.72
    Activations Density 0.685%

    No Known Activations