© 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. 66857
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
    maktadır
    -1.09
     gradualmente
    -1.06
     APPELLANT
    -1.05
     APPELL
    -1.05
    Followers
    -0.98
    ballon
    -0.98
     harika
    -0.97
     favoriser
    -0.96
    鐺
    -0.96
     estudantes
    -0.93
    POSITIVE LOGITS
     their
    1.39
    店的
    1.14
     really
    0.99
    Now
    0.98
     even
    0.96
     they
    0.96
    Even
    0.96
     particularly
    0.95
    tivos
    0.94
     now
    0.94
    Activations Density 0.079%

    No Known Activations