© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    Cascading Style Sheets)

    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
     Judges
    1.68
     chod
    1.53
     Founders
    1.48
    erte
    1.46
     Races
    1.46
     kik
    1.45
    সাথে
    1.44
    𝙚
    1.44
    들은
    1.41
    er
    1.40
    POSITIVE LOGITS
    <unused2179>
    1.87
     صفر
    1.85
     பூஜை
    1.84
    ವೇಂದ್ರ
    1.81
    ExpNow
    1.78
     toneladas
    1.69
     பூஜ
    1.65
    <unused1030>
    1.64
    ربعة
    1.63
    bangan
    1.60
    Activations Density 0.064%

    No Known Activations