© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128030
    Prev
    Next
    INDEX
    Explanations

    interjections like ah, ih, eh, uh

    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_22/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
    </h3>
    -3.06
     was
    -2.72
    guigu
    -2.58
    焄
    -2.42
     müssen
    -2.28
    罽
    -2.22
    más
    -2.20
    谖
    -2.19
    !”
    -2.19
    бора
    -2.17
    POSITIVE LOGITS
    s
    4.59
    (
    2.83
    .
    2.70
    </b>
    2.56
    M
    2.55
    }$
    2.48
     Moved
    2.44
     Kept
    2.22
    derdag
    2.16
    ᠌
    2.13
    Activations Density 0.137%

    No Known Activations