© 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. 34-GEMMASCOPE-RES-131K
    7. 110588
    Prev
    Next
    INDEX
    Explanations

    cause, restart, coupled, constituency

    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_34/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
     التجار
    -0.79
     Returns
    -0.76
     RTP
    -0.73
    綦
    -0.73
    venom
    -0.71
    ociação
    -0.69
     śmierci
    -0.69
     Stowe
    -0.68
     MAM
    -0.67
    ENOS
    -0.67
    POSITIVE LOGITS
     poudre
    0.68
    Markov
    0.67
    Inver
    0.65
    𝗼
    0.64
    kola
    0.63
     Madness
    0.63
    кту
    0.63
    lineHeight
    0.63
    Nieuw
    0.63
     Schein
    0.62
    Activations Density 0.131%

    No Known Activations