© 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. 86982
    Prev
    Next
    INDEX
    Explanations

    forms of to be followed by state

    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
    3
    -2.30
    7
    -2.16
    6
    -2.14
    4
    -2.11
    What
    -2.03
    5
    -2.02
    9
    -1.94
     would
    -1.77
     of
    -1.73
    8
    -1.72
    POSITIVE LOGITS
     in
    2.55
     there
    2.03
     on
    1.94
     at
    1.55
    licante
    1.53
    andere
    1.48
    🦣
    1.43
    izziness
    1.41
    ⁂
    1.40
    anderen
    1.39
    Activations Density 0.131%

    No Known Activations