© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6895
    Prev
    Next
    INDEX
    Explanations

    Fibonacci

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EXPER
    0.87
     방법에
    0.85
    Exper
    0.81
     टिप्स
    0.78
    Expert
    0.77
    exper
    0.76
    査
    0.76
    ジット
    0.76
    expert
    0.74
    빨
    0.74
    POSITIVE LOGITS
     cofactor
    0.88
    orn
    0.82
     mv
    0.77
    𝓂
    0.77
    umen
    0.76
    onos
    0.76
    মান
    0.75
     septum
    0.75
    umption
    0.74
     мем
    0.74
    Activations Density 0.029%

    No Known Activations