© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14982
    Prev
    Next
    INDEX
    Explanations

    programming conditionals and data structures

    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
     estúdio
    -1.23
     espelho
    -1.14
    之事
    -1.13
    ܜ
    -1.08
     promesas
    -1.08
     ônibus
    -1.06
     namorado
    -1.02
    luk
    -1.02
     avião
    -1.00
     caminhão
    -0.99
    POSITIVE LOGITS
    侑
    1.09
     and
    1.09
    了一种
    1.08
    럼
    1.05
    —”
    1.01
    "—
    0.98
    んだから
    0.98
    ——”
    0.98
     rabat
    0.97
    CCIÓN
    0.96
    Activations Density 0.005%

    No Known Activations