© 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. 22-GEMMASCOPE-RES-131K
    7. 33446
    Prev
    Next
    INDEX
    Explanations

    navigation drawer template

    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
    汆
    -1.14
    子さん
    -1.13
    </em>
    -1.12
     indivíduo
    -1.10
     brauchst
    -1.08
    ;&
    -1.08
     empieza
    -1.07
    ；
    -1.07
    迅速
    -1.04
    也得
    -1.04
    POSITIVE LOGITS
    idados
    1.21
    讀書
    1.20
    Муж
    1.17
    おはよう
    1.10
    やろ
    1.09
    грамм
    1.09
    pergillus
    1.08
    Acne
    1.06
     asemenea
    1.05
    Украина
    1.05
    Activations Density 0.003%

    No Known Activations