© 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. 100303
    Prev
    Next
    INDEX
    Explanations

    layout demo comparison superpower Q

    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
     сообщили
    -1.73
     españa
    -1.65
     récord
    -1.63
    Tienen
    -1.45
     reafon
    -1.38
     tirantes
    -1.34
     fufficient
    -1.30
     alemania
    -1.30
    žku
    -1.30
     fuper
    -1.30
    POSITIVE LOGITS
     with
    1.47
     Eigentü
    1.40
    ennom
    1.36
    有时候
    1.34
     but
    1.33
     हालांकि
    1.26
     across
    1.26
     lorsque
    1.25
     risultato
    1.24
     синд
    1.23
    Activations Density 0.000%

    No Known Activations