© 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. 99282
    Prev
    Next
    INDEX
    Explanations

    in short supply

    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
    idän
    -0.79
     Rigidbody
    -0.74
    setView
    -0.74
     grossesse
    -0.71
    glycemia
    -0.71
    čním
    -0.69
    IdList
    -0.69
     invitados
    -0.68
    WORKING
    -0.68
    CBN
    -0.68
    POSITIVE LOGITS
     short
    4.50
    short
    3.59
    Short
    3.16
     Short
    2.95
    短
    2.92
    SHORT
    2.77
     SHORT
    2.75
     shortage
    2.64
     корот
    2.33
    ショート
    2.27
    Activations Density 0.026%

    No Known Activations