© 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. 71063
    Prev
    Next
    INDEX
    Explanations

    connecting nouns

    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
    </h1>
    -1.50
    parole
    -1.41
    діа
    -1.30
    銑
    -1.28
    surveys
    -1.28
    mX
    -1.27
    pulsar
    -1.27
     INCLUDES
    -1.27
    ADVERTISEMENT
    -1.24
    accor
    -1.24
    POSITIVE LOGITS
    ed
    1.49
    ion
    1.48
    ad
    1.42
    tu
    1.41
    ではまた
    1.40
    tt
    1.40
    cha
    1.38
    k
    1.37
    ing
    1.35
    od
    1.35
    Activations Density 0.098%

    No Known Activations