© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2551
    Prev
    Next
    INDEX
    Explanations

    questions starts with what why how

    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
    it
    2.36
    et
    2.22
     …
    1.81
    っ
    1.74
    و
    1.69
    ul
    1.67
    みに
    1.62
    …
    1.60
    Globe
    1.56
     Might
    1.55
    POSITIVE LOGITS
    zynarod
    2.35
     '^
    2.06
    鿷
    2.06
    នូវ
    2.03
    㝅
    1.99
    zovaniyu
    1.97
    <unused893>
    1.97
    篂
    1.97
    TabText
    1.95
     vuccanti
    1.95
    Activations Density 0.279%

    No Known Activations