© 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. 44443
    Prev
    Next
    INDEX
    Explanations

    prefacing context or examples

    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
     and
    -2.03
     both
    -2.03
    "},
    -2.00
    As
    -2.00
     anstatt
    -1.88
    You
    -1.87
    From
    -1.84
    %?
    -1.82
    le
    -1.81
    also
    -1.80
    POSITIVE LOGITS
    ᥬ
    1.70
    Natürlich
    1.67
    unser
    1.66
    罴
    1.63
    嚒
    1.63
     interessant
    1.59
    Jetzt
    1.55
    actéristi
    1.54
    Ausgabe
    1.54
    </sup>
    1.53
    Activations Density 0.086%

    No Known Activations