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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    Federal Trade Commission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yz
    1.59
    y
    1.54
    ichlet
    1.51
    Lowercase
    1.41
    NAME
    1.41
    none
    1.37
    marginBottom
    1.37
    yards
    1.36
    থাৎ
    1.35
    lords
    1.33
    POSITIVE LOGITS
     gramos
    1.56
    то
    1.55
    тки
    1.55
    ок
    1.50
     บาท
    1.46
    و
    1.45
    acions
    1.43
    waar
    1.40
    𝘴
    1.40
    ರು
    1.39
    Activations Density 0.000%

    No Known Activations