© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3903
    Prev
    Next
    INDEX
    Explanations

    reflection, concentration, perspective, accumulation

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    pesar
    1.03
    ì
    1.03
    ʼ
    1.02
    inda
    0.98
     afuera
    0.97
    ̌
    0.97
    agh
    0.95
     completar
    0.95
    ભગ
    0.94
    istes
    0.93
    POSITIVE LOGITS
    ؕ
    1.04
    سر
    0.99
    cpu
    0.98
     '/'
    0.95
    natures
    0.92
    e
    0.92
    <unused356>
    0.90
    threaded
    0.89
    CID
    0.88
     °,
    0.88
    Activations Density 0.000%

    No Known Activations