© 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. 92883
    Prev
    Next
    INDEX
    Explanations

    XML mapping rules

    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
    ラ
    -0.75
    Finance
    -0.74
     杨
    -0.73
    Grilled
    -0.72
    之力
    -0.72
    ಛ
    -0.70
    ucap
    -0.70
     APT
    -0.70
    ůj
    -0.69
    érales
    -0.69
    POSITIVE LOGITS
    }$
    0.76
     hardships
    0.75
    汲
    0.74
    vins
    0.73
    acia
    0.72
    }}$
    0.72
    PointerException
    0.71
    onne
    0.71
     iné
    0.71
    '$
    0.70
    Activations Density 0.004%

    No Known Activations