© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    string declaration with subsequent action

    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
     وخ
    1.79
    whole
    1.68
    綦
    1.59
    ्ठा
    1.59
    Towards
    1.56
    Whole
    1.55
     toda
    1.55
    કાર
    1.55
    ്
    1.52
    Sine
    1.51
    POSITIVE LOGITS
    蜓
    1.74
    มาชิก
    1.66
     Adirond
    1.60
    𝒐
    1.60
    erdale
    1.59
    𝒊
    1.54
     amer
    1.53
    icono
    1.50
    ceso
    1.49
    viendo
    1.49
    Activations Density 0.050%

    No Known Activations