© 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. 35018
    Prev
    Next
    INDEX
    Explanations

    alogenator

    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
    umacher
    -1.21
    G
    -1.13
    A
    -1.08
    がっ
    -1.05
    ari
    -1.01
    ER
    -1.01
    急に
    -1.01
    N
    -1.00
     terapé
    -0.99
    えっ
    -0.98
    POSITIVE LOGITS
     reporta
    1.01
    وصلات
    0.92
    ceptable
    0.91
    lewati
    0.91
     later
    0.91
     through
    0.91
     súper
    0.90
    慮
    0.90
     آمریک
    0.89
     kapturem
    0.89
    Activations Density 0.125%

    No Known Activations