© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3192
    Prev
    Next
    INDEX
    Explanations

    listing disadvantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    attere
    1.64
    绪
    1.57
    itre
    1.55
    izações
    1.48
     Lij
    1.45
    いく
    1.44
    řej
    1.41
     pubblica
    1.40
    ğe
    1.38
     linéaires
    1.38
    POSITIVE LOGITS
    痪
    2.17
    kinase
    1.83
    coelastic
    1.83
    ambuf
    1.74
    erjee
    1.74
    合わせ
    1.71
    vocals
    1.69
    gars
    1.67
    אות
    1.66
     ashes
    1.66
    Activations Density 0.508%

    No Known Activations