© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    leading zeros or numeric prefixes

    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
    ek
    1.92
    eea
    1.83
    𝒅
    1.79
     paperwork
    1.76
     stocked
    1.74
    𝒕
    1.72
    power
    1.66
     cavity
    1.59
     power
    1.59
    𝒉
    1.59
    POSITIVE LOGITS
    ات
    1.71
     CCc
    1.71
    setzungen
    1.58
    톡
    1.58
    ğından
    1.54
     ریس
    1.53
     '!
    1.53
     przest
    1.52
    لم
    1.51
    귿
    1.51
    Activations Density 0.079%

    No Known Activations