© 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. 179713
    Prev
    Next
    INDEX
    Explanations

    grown, bundles, peer, affiliates

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

    perceived [quality/outcome/interest/severity]

    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
    using
    0.46
     delta
    0.46
     carelessly
    0.42
    in
    0.40
    corr
    0.38
     elapse
    0.38
    })
    0.38
    iven
    0.38
     imply
    0.38
     mediana
    0.37
    POSITIVE LOGITS
     తాజాగా
    0.55
    𝓇
    0.49
     savior
    0.48
     ﷺ
    0.47
     数
    0.46
     จน
    0.46
     fi
    0.46
     çi
    0.46
     Callable
    0.46
    revalidator
    0.45
    Activations Density 0.000%

    No Known Activations