© 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. 22-GEMMASCOPE-RES-131K
    7. 15626
    Prev
    Next
    INDEX
    Explanations

    specific names and code constructs

    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_22/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
    //}
    -1.00
    "],
    -0.98
    ()]
    -0.98
    corrhi
    -0.97
    धन
    -0.93
     vernac
    -0.92
     escritora
    -0.89
    '],
    -0.89
    )));
    -0.88
    énus
    -0.88
    POSITIVE LOGITS
    co
    1.00
    ¨
    0.95
     dị
    0.93
     vectoriales
    0.92
    װ
    0.88
     agon
    0.86
     वाला
    0.86
     поэтому
    0.86
     was
    0.85
    mmation
    0.85
    Activations Density 0.000%

    No Known Activations