© 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. 39337
    Prev
    Next
    INDEX
    Explanations

    programmatic terms

    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
     of
    -2.41
    ти
    -2.38
     We
    -2.31
     самого
    -2.22
    也不用
    -2.16
     ruines
    -2.14
     cause
    -2.09
    頷
    -1.95
     continuar
    -1.94
    ឵
    -1.93
    POSITIVE LOGITS
    the
    2.94
    term
    2.45
    S
    2.42
    ),
    2.31
    what
    2.30
    \
    2.19
    L
    2.11
    T
    2.09
    ляции
    2.08
     необхідно
    2.08
    Activations Density 0.015%

    No Known Activations