© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70394
    Prev
    Next
    INDEX
    Explanations

    terms of use and contracts

    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
     who
    -1.59
     thanks
    -1.47
    cisive
    -1.31
    vasive
    -1.31
     ἡ
    -1.26
     eftersom
    -1.24
    Huile
    -1.23
    搋
    -1.23
     executar
    -1.23
     καὶ
    -1.20
    POSITIVE LOGITS
     idén
    1.29
    )　
    1.26
     mindestens
    1.26
    A
    1.21
    varlak
    1.19
    <bos>
    1.16
    jö
    1.15
    :
    1.13
    accessToken
    1.11
    呐
    1.09
    Activations Density 0.107%

    No Known Activations