© 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. 20462
    Prev
    Next
    INDEX
    Explanations

    causal discovery

    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
     Familie
    0.51
     フル
    0.49
     Lebens
    0.48
     Jahrhundert
    0.47
     mit
    0.46
    ﻟ
    0.46
     Kata
    0.45
    '
    0.45
     I
    0.44
    .
    0.44
    POSITIVE LOGITS
    나
    0.47
    istic
    0.46
    le
    0.45
    itives
    0.44
    zones
    0.44
    MLLoader
    0.43
    WEEN
    0.42
    warming
    0.41
     breweries
    0.41
    یل
    0.41
    Activations Density 0.000%

    No Known Activations