© 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. 59029
    Prev
    Next
    INDEX
    Explanations

    Hers, Hershey, Herschel

    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
     he
    -2.92
    }
    -2.67
     så
    -2.22
     forState
    -2.17
    ৢ
    -2.16
    на
    -2.14
     könne
    -2.11
    皞
    -2.11
     musst
    -2.09
     बहुत
    -2.08
    POSITIVE LOGITS
    ’
    2.36
    烀
    2.31
     verschied
    2.30
    问道
    2.30
    ,’
    2.28
     WAY
    2.23
    dign
    2.23
     begleiten
    2.20
    ية
    2.19
     puisi
    2.19
    Activations Density 0.006%

    No Known Activations