© 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. 224970
    Prev
    Next
    INDEX
    Explanations

    fresh milk, preprocessor

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

    phrase "consider me"

    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
    '
    0.52
     OUT
    0.51
     et
    0.49
    </i>
    0.44
    マット
    0.44
    面
    0.44
     additional
    0.42
     Sergi
    0.42
     EDUC
    0.42
     ET
    0.41
    POSITIVE LOGITS
    🚦
    0.46
     Старки
    0.45
    شود
    0.45
    🚥
    0.44
     или
    0.44
    AutoFocus
    0.44
     विरुद्ध
    0.44
    нити
    0.43
    ómicas
    0.43
    },-\
    0.42
    Activations Density 0.001%

    No Known Activations