© 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. 119783
    Prev
    Next
    INDEX
    Explanations

    final edits and next steps

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

    significant portion of

    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
    َى
    0.48
     devad
    0.48
    ASS
    0.45
     narc
    0.45
     propagand
    0.45
     weak
    0.44
    È
    0.44
     wrath
    0.44
     巻
    0.43
    iaxial
    0.43
    POSITIVE LOGITS
     Tuning
    0.52
     Conditioner
    0.52
     Escape
    0.50
    ፍ
    0.49
    get
    0.48
     Voting
    0.46
    can
    0.45
     Automation
    0.45
     Tune
    0.44
    twe
    0.44
    Activations Density 0.000%

    No Known Activations