© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24594
    Prev
    Next
    INDEX
    Explanations

    connectors, cables, and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.52
     someone
    0.45
    P
    0.43
    bre
    0.43
     BRE
    0.43
     W
    0.42
     P
    0.42
    Acad
    0.41
    °
    0.40
     “
    0.39
    POSITIVE LOGITS
     అంబేద్కర్
    0.50
    ColumnKind
    0.49
     göra
    0.47
     säker
    0.47
    tsioon
    0.46
    <unused2038>
    0.46
    MathMarks
    0.46
     drücken
    0.45
     सियासी
    0.45
    perturbative
    0.44
    Activations Density 0.001%

    No Known Activations