© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207836
    Prev
    Next
    INDEX
    Explanations

    IT solutions

    np_acts-logits-general · gemini-2.5-flash-lite

    Maria Rodriguez, rage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ✂
    0.48
    viron
    0.45
    Serial
    0.45
    icode
    0.44
    serial
    0.44
     SERIAL
    0.44
    Memorial
    0.43
    dirty
    0.43
    monitoring
    0.42
     clean
    0.42
    POSITIVE LOGITS
    𝗵
    0.54
     seguidores
    0.51
     ripples
    0.51
     Melanes
    0.51
     در
    0.49
     رپورٹ
    0.47
    ЕМ
    0.47
     autistic
    0.46
     membres
    0.46
    ورس
    0.46
    Activations Density 0.002%

    No Known Activations