© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 762
    Prev
    Next
    INDEX
    Explanations

    names followed by said

    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
    !
    -1.64
     publicó
    -1.55
     zahlreichen
    -1.47
     beiden
    -1.45
    回到了
    -1.43
     даже
    -1.42
     proporcionan
    -1.39
     but
    -1.39
     nossas
    -1.38
     realizó
    -1.38
    POSITIVE LOGITS
     also
    2.48
     always
    1.88
     that
    1.71
     now
    1.66
     said
    1.65
     zwi
    1.54
     constantly
    1.32
     etui
    1.32
     it
    1.31
     étages
    1.30
    Activations Density 0.308%

    No Known Activations