© 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. 46466
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    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
    SBOM
    0.49
     সম্পদের
    0.47
     पढ़ाने
    0.44
    νοι
    0.43
    ֆ
    0.43
    휀
    0.43
    రాలు
    0.43
    𝚏
    0.43
    ཥ
    0.43
    ivanja
    0.42
    POSITIVE LOGITS
     simplex
    0.51
     Triumph
    0.42
     Indo
    0.42
     perist
    0.42
     triumph
    0.41
     States
    0.41
     semplic
    0.41
     initially
    0.40
     typing
    0.40
     yle
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.