© 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. 10-GEMMASCOPE-RES-131K
    7. 59544
    Prev
    Next
    INDEX
    Explanations

    words beginning with har

    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_10/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
    缦
    -3.06
    甞
    -3.03
    
    -2.98
     advir
    -2.86
    鳢
    -2.80
    
    -2.80
     decidido
    -2.80
    떳
    -2.78
     insectes
    -2.78
    哒
    -2.77
    POSITIVE LOGITS
    3
    4.03
    0
    3.73
    1
    3.72
    2
    3.47
    7
    3.41
    }
    3.39
    In
    3.19
    s
    3.19
     "
    3.16
    <i>
    3.08
    Activations Density 0.016%

    No Known Activations