© 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. 43938
    Prev
    Next
    INDEX
    Explanations

    concessive conjunctions

    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
    </u>
    -1.53
     financieras
    -1.52
    }
    -1.52
     also
    -1.52
     are
    -1.52
    i
    -1.48
    of
    -1.46
    po
    -1.44
    .”
    -1.44
    S
    -1.43
    POSITIVE LOGITS
     péro
    1.76
     raccont
    1.69
    緜
    1.66
    ⇴
    1.60
    珦
    1.57
     fosse
    1.54
    roves
    1.52
    想起
    1.52
    купить
    1.49
     silueta
    1.49
    Activations Density 0.007%

    No Known Activations