© 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. 34-GEMMASCOPE-RES-131K
    7. 99244
    Prev
    Next
    INDEX
    Explanations

    action followed by direction

    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_34/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
    ‌شده
    -0.72
     popraw
    -0.68
    titious
    -0.68
    filler
    -0.68
     drugie
    -0.67
    jegy
    -0.66
    ‌کنندگان
    -0.66
    ̺
    -0.65
     세계
    -0.65
     Aik
    -0.64
    POSITIVE LOGITS
    back
    1.59
    through
    1.23
    backs
    1.19
    BACK
    1.16
     back
    1.14
    Back
    1.05
    thru
    1.02
    回
    0.98
     Cowboy
    0.90
    down
    0.89
    Activations Density 0.048%

    No Known Activations