© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14056
    Prev
    Next
    INDEX
    Explanations

    specific syntax characters

    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
     also
    -1.09
    ne
    -1.00
    is
    -1.00
    se
    -0.99
     dessutom
    -0.97
    更何况
    -0.97
    但也
    -0.96
    on
    -0.95
    ni
    -0.94
    但却
    -0.93
    POSITIVE LOGITS
     ofici
    1.10
     ahorro
    1.09
    ahkan
    1.08
    klara
    1.08
     Deixe
    1.07
    Ngoài
    1.06
    Firstly
    1.05
    殽
    1.05
     verhind
    1.04
    ЗУ
    1.02
    Activations Density 0.002%

    No Known Activations