© 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. 30687
    Prev
    Next
    INDEX
    Explanations

    scientists, it, buy, be

    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
     in
    0.85
    s
    0.76
     a
    0.61
    ים
    0.58
    いる
    0.57
    ों
    0.54
     In
    0.53
     extruded
    0.52
     distortion
    0.52
     pervasive
    0.50
    POSITIVE LOGITS
    т
    0.48
    жные
    0.46
    dera
    0.46
    jería
    0.44
    PatientR
    0.44
    <unused2138>
    0.43
    šení
    0.43
    జ్
    0.42
    的部分
    0.42
     maravill
    0.42
    Activations Density 0.050%

    No Known Activations