© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58723
    Prev
    Next
    INDEX
    Explanations

    Scanner in, referred to

    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
     prolly
    -0.76
    谷川
    -0.75
    انس
    -0.74
    豉
    -0.73
     poveznice
    -0.71
     台北
    -0.70
     första
    -0.69
    лайн
    -0.69
    ABAJO
    -0.68
     Maximal
    -0.67
    POSITIVE LOGITS
    Kön
    0.85
     agonizing
    0.83
    جوی
    0.81
    Zahl
    0.79
     hilfreich
    0.77
    })(
    0.77
    ীয়
    0.76
    vorschau
    0.74
     ocul
    0.73
    illés
    0.73
    Activations Density 0.007%

    No Known Activations