© 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. 10-GEMMASCOPE-RES-131K
    7. 20900
    Prev
    Next
    INDEX
    Explanations

    actions with consequences

    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
     two
    -1.63
     ruangan
    -1.45
     
    -1.38
    Two
    -1.37
    ervare
    -1.34
    IFUL
    -1.33
     ratusan
    -1.31
     pendukung
    -1.30
     keseluruhan
    -1.30
     sposa
    -1.29
    POSITIVE LOGITS
     who
    1.90
     their
    1.37
     themselves
    1.34
    .
    1.33
    kespea
    1.23
     Their
    1.16
    -
    1.16
    перед
    1.15
    ok
    1.14
     ihrer
    1.14
    Activations Density 0.180%

    No Known Activations