© 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. 34-GEMMASCOPE-RES-131K
    7. 64594
    Prev
    Next
    INDEX
    Explanations

    card types and residency

    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
    술
    -0.84
    Cola
    -0.75
     melk
    -0.74
     sasa
    -0.74
    BAR
    -0.73
     contraintes
    -0.73
    ELL
    -0.72
    STAND
    -0.72
    Native
    -0.72
    ğmen
    -0.72
    POSITIVE LOGITS
     card
    3.02
     cards
    2.78
    card
    2.23
     Cards
    2.00
     Card
    2.00
    cards
    1.95
    Cards
    1.69
    Card
    1.66
    カード
    1.63
     tarjeta
    1.46
    Activations Density 0.022%

    No Known Activations