© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79866
    Prev
    Next
    INDEX
    Explanations

    assignments or variable declarations

    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
     those
    -0.94
    Essentially
    -0.93
     حوزه
    -0.89
    そういう
    -0.86
    Technically
    -0.85
    Similarly
    -0.83
     ambil
    -0.82
     polie
    -0.81
     choses
    -0.81
    Possibly
    -0.80
    POSITIVE LOGITS
     его
    1.05
     ее
    0.98
     handelt
    0.90
    ⎧
    0.90
    unta
    0.87
     vroeger
    0.84
    利
    0.84
    -{
    0.84
    ('
    0.82
     vermeld
    0.82
    Activations Density 0.032%

    No Known Activations