© 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. 112376
    Prev
    Next
    INDEX
    Explanations

    even though contrast

    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
    ’
    -1.70
    因为它
    -1.68
    }$
    -1.63
    }
    -1.61
    </b>
    -1.55
    \
    -1.52
    )?
    -1.49
    Hadi
    -1.49
    ))
    -1.46
    -
    -1.46
    POSITIVE LOGITS
     olduk
    1.66
     this
    1.64
    .}(
    1.62
     your
    1.52
    欸
    1.51
     nantinya
    1.50
     olacaktır
    1.45
    蓠
    1.42
    *}[
    1.41
    呦
    1.41
    Activations Density 0.004%

    No Known Activations