© 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. 103722
    Prev
    Next
    INDEX
    Explanations

    on the one hand

    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
     will
    -1.66
     is
    -1.55
     or
    -1.41
     öpp
    -1.41
     with
    -1.40
     every
    -1.39
     which
    -1.37
     from
    -1.37
     who
    -1.36
     also
    -1.34
    POSITIVE LOGITS
    沨
    1.63
     rodea
    1.63
    拊
    1.44
     })}
    1.42
     à
    1.41
    ſtra
    1.41
     ás
    1.40
    𖥦
    1.38
     afront
    1.37
     jóvenes
    1.36
    Activations Density 0.025%

    No Known Activations