© 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. 22-GEMMASCOPE-RES-131K
    7. 129583
    Prev
    Next
    INDEX
    Explanations

    speed slower, camel multicast

    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_22/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
    loggen
    -1.20
    contentView
    -1.13
    ckeye
    -1.06
    Hoping
    -1.04
    himself
    -1.03
    imageio
    -1.03
     една
    -1.02
    testen
    -1.02
     harus
    -1.00
    orses
    -0.99
    POSITIVE LOGITS
     is
    1.16
     Longitud
    1.02
    ละเอ
    1.01
     Geologic
    0.98
     Solicit
    0.92
     schuhe
    0.90
    1
    0.90
     may
    0.89
     we
    0.88
     Deriv
    0.87
    Activations Density 0.000%

    No Known Activations