© 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. 2414
    Prev
    Next
    INDEX
    Explanations

    sticky backing

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

    list, continues, and breaks

    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
     व्हेल
    0.49
     तिजारत
    0.48
     харак
    0.48
    la
    0.47
    >)</
    0.47
     Това
    0.47
    läge
    0.47
     entscheiden
    0.46
     оке
    0.46
     पार्टी
    0.46
    POSITIVE LOGITS
    EL
    0.50
    }$\
    0.43
    還有
    0.43
    Submitted
    0.42
    还有
    0.40
    விடும்
    0.40
     Winkler
    0.40
     destruir
    0.39
     Liqu
    0.39
    }$\\
    0.39
    Activations Density 0.000%

    No Known Activations