© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145904
    Prev
    Next
    INDEX
    Explanations

    Penn Station, Jersey City

    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_29_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
    ীতি
    0.74
     formContext
    0.71
     wParam
    0.70
    erea
    0.69
     высоту
    0.69
    衮
    0.68
     канторы
    0.68
    
    0.67
    VIDOR
    0.67
    كيد
    0.67
    POSITIVE LOGITS
    טח
    0.81
    JS
    0.77
    リ
    0.76
    מס
    0.76
    MARKS
    0.76
    Signs
    0.74
    ADY
    0.74
    ಟ್ಟು
    0.74
    وبی
    0.73
    Bytes
    0.72
    Activations Density 0.001%

    No Known Activations