© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10751
    Prev
    Next
    INDEX
    Explanations

    budget estimates and costs

    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
    prés
    2.13
    प
    2.00
    करने
    2.00
    ூ
    1.97
    ">→</
    1.95
    यह
    1.93
    फ़
    1.93
    aw
    1.89
    బో
    1.85
     করিয়৷
    1.83
    POSITIVE LOGITS
     Filed
    1.83
     Anterior
    1.80
     Lateral
    1.71
     Mills
    1.68
    .
    1.67
     Administrative
    1.65
     Dors
    1.63
     Obit
    1.60
     Invit
    1.60
    yzed
    1.58
    Activations Density 0.006%

    No Known Activations