© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195135
    Prev
    Next
    INDEX
    Explanations

    about [topic]

    np_acts-logits-general · gemini-2.5-flash-lite

    powerful attractor, threshold, handle both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    겪
    0.46
     couper
    0.45
    ക്കളുടെ
    0.43
    overlapping
    0.43
    ರ್ಗ
    0.42
    ன்ன
    0.42
     क्लाइ
    0.41
    ர்
    0.41
    谊
    0.41
    sentiment
    0.41
    POSITIVE LOGITS
    </strong>
    0.47
     тях
    0.46
    apur
    0.46
    이었다
    0.45
     imediat
    0.44
    </b>
    0.44
    </h4>
    0.44
     всей
    0.44
    8
    0.43
     mucho
    0.43
    Activations Density 0.001%

    No Known Activations