© 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. 12271
    Prev
    Next
    INDEX
    Explanations

    input validation

    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
    ly
    2.62
    ське
    2.47
    깐
    2.39
    nya
    2.38
    టీ
    2.28
     wą
    2.24
    ら
    2.22
    di
    2.20
    сь
    2.17
    ך
    2.14
    POSITIVE LOGITS
    ঁচা
    2.76
    aient
    2.74
    tions
    2.72
     कटा
    2.71
    tension
    2.64
    aat
    2.61
    স্র
    2.61
    anın
    2.59
    त
    2.56
     limite
    2.54
    Activations Density 0.008%

    No Known Activations