© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    extend, withColumn, WITH, WITHIN GROUP

    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
    a
    2.72
    一遍
    2.62
    ي
    2.54
    IA
    2.48
    嗘
    2.48
    ை
    2.41
    ל
    2.38
    aspect
    2.36
    strconv
    2.34
    רג
    2.30
    POSITIVE LOGITS
    रासत
    2.63
     lingkaran
    2.56
     lapangan
    2.53
    वानिव
    2.49
    レスレット
    2.49
     Daerah
    2.49
    ایل
    2.47
    imab
    2.40
    쫑
    2.39
    cionario
    2.38
    Activations Density 0.010%

    No Known Activations