© 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. 10395
    Prev
    Next
    INDEX
    Explanations

    micro- prefix

    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
    Not in Any Lists

    No Comments

    Negative Logits
    मर्रा
    3.58
    iness
    2.90
    inko
    2.82
    tenance
    2.80
    pF
    2.80
    celain
    2.79
    sburg
    2.77
    ┼
    2.72
    ✽
    2.69
    lof
    2.64
    POSITIVE LOGITS
    자
    2.81
    Impl
    2.46
    TIM
    2.40
    歹
    2.34
    자인
    2.33
    D
    2.27
    N
    2.25
    ுகிறது
    2.25
    TQ
    2.17
    क्स्ट
    2.17
    Activations Density 0.026%

    No Known Activations