© 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. 10-GEMMASCOPE-RES-131K
    7. 43615
    Prev
    Next
    INDEX
    Explanations

    names following edmund or eleanor

    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
    t
    -2.91
    m
    -2.84
     But
    -2.81
     値下げ
    -2.81
     }
    -2.58
    e
    -2.44
    a
    -2.44
    f
    -2.42
     другое
    -2.42
    豋
    -2.41
    POSITIVE LOGITS
    “
    2.77
    狆
    2.48
    𐄁
    2.41
    llten
    2.41
    }
    2.38
    </i>
    2.30
    驁
    2.20
    囖
    2.19
    ции
    2.17
    玊
    2.16
    Activations Density 0.008%

    No Known Activations