© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117276
    Prev
    Next
    INDEX
    Explanations

    fixed modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ATO
    -0.90
    逦
    -0.90
    Kenmerken
    -0.85
     sekitar
    -0.82
    
    -0.82
    attacks
    -0.82
     AGC
    -0.80
     animali
    -0.80
     REA
    -0.80
     familles
    -0.79
    POSITIVE LOGITS
     fixed
    2.42
     Fixed
    2.28
    fixed
    2.22
    Fixed
    2.14
    固定
    1.69
     FIXED
    1.63
    FIXED
    1.63
     Fix
    1.60
     fix
    1.55
     fixes
    1.47
    Activations Density 0.021%

    No Known Activations