© 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. 11955
    Prev
    Next
    INDEX
    Explanations

    signal properties and processing

    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
    다면
    2.80
    (':')[
    2.44
    HING
    2.42
    얗
    2.39
    ny
    2.33
    털
    2.30
    둠
    2.25
    matchCondition
    2.24
    ‖</
    2.24
    쨰
    2.21
    POSITIVE LOGITS
    a
    3.15
    цион
    3.07
     Н
    3.00
     luminescence
    2.93
    Ꮙ
    2.93
    د
    2.90
    ция
    2.90
     formation
    2.89
     contraception
    2.89
    ेंशन
    2.89
    Activations Density 0.017%

    No Known Activations