© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29023
    Prev
    Next
    INDEX
    Explanations

    adjustment in language

    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
    Faces
    0.40
     Spears
    0.38
     G
    0.37
     λόγω
    0.37
     Faces
    0.37
     انجام
    0.36
     گ
    0.36
    当时
    0.36
     Vold
    0.36
    ตำบล
    0.36
    POSITIVE LOGITS
     oils
    0.38
     copolymers
    0.35
     waterproofing
    0.35
     bias
    0.34
    ರಳ
    0.34
     बिख
    0.33
     glBindTexture
    0.33
    <h3>
    0.33
    atios
    0.32
    amending
    0.32
    Activations Density 0.001%

    No Known Activations