© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118707
    Prev
    Next
    INDEX
    Explanations

    category names

    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
    vie
    -0.75
     ViewModel
    -0.74
     ())
    -0.72
     readout
    -0.66
    view
    -0.66
     read
    -0.66
     Luftwaffe
    -0.66
    ᒪ
    -0.65
     foliar
    -0.65
    ffff
    -0.65
    POSITIVE LOGITS
    ívar
    0.71
    фессиона
    0.70
     tage
    0.67
    orges
    0.66
    管理员
    0.66
     Clifford
    0.66
    Loss
    0.66
    ragalactic
    0.65
    つく
    0.63
    方が
    0.63
    Activations Density 0.074%

    No Known Activations