© 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. 15062
    Prev
    Next
    INDEX
    Explanations

    numbers followed by colons

    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
    contentText
    0.43
    irin
    0.42
    `(
    0.41
     मिलियन
    0.40
    সপ
    0.40
    𝑘
    0.39
    4
    0.39
    𝑆
    0.39
    handel
    0.39
    belong
    0.39
    POSITIVE LOGITS
     reliability
    0.47
     mitologia
    0.46
     particulière
    0.45
     particular
    0.41
     digs
    0.40
     Reliability
    0.39
     Emeritus
    0.39
     espec
    0.39
     lore
    0.39
     clair
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.