© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    html title

    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_22_width_16k_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
    ﺭ
    1.06
    和小
    1.05
     betekent
    1.01
    ಷ್ಟ
    1.01
     ühe
    0.95
     whanne
    0.94
    ši
    0.94
    Honestly
    0.92
    rectionType
    0.92
     wajah
    0.92
    POSITIVE LOGITS
    પા
    0.81
     Inca
    0.80
    ה
    0.80
    course
    0.79
     computers
    0.79
     transfers
    0.78
     μετα
    0.78
     BP
    0.78
     computador
    0.76
    (&(
    0.76
    Activations Density 0.015%

    No Known Activations