© 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. 138322
    Prev
    Next
    INDEX
    Explanations

    file extension `.xlsx`

    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
     transforma
    0.49
    டிக்க
    0.44
     politiques
    0.44
    ϡ
    0.42
     তৎপর
    0.42
     Bollinger
    0.42
     contempla
    0.42
     sentiments
    0.41
    نى
    0.41
    ్రె
    0.40
    POSITIVE LOGITS
    Snow
    0.49
    Gravity
    0.46
    ढ़ाई
    0.43
    Squirrel
    0.42
    는
    0.42
    Sky
    0.41
    Left
    0.41
    Star
    0.41
     snow
    0.41
    Certificate
    0.40
    Activations Density 0.003%

    No Known Activations