© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    code snippets and structural elements

    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
    。《
    1.10
    。\
    1.09
    ;}
    1.08
    }.
    1.06
    ;.
    1.04
    »;
    1.02
    」。
    1.01
    '!
    1.01
    ا۔
    1.00
    。.
    1.00
    POSITIVE LOGITS
     bandwagon
    0.70
     section
    0.67
     seção
    0.65
     bivariate
    0.65
     cohort
    0.65
     కార్యక్రమంలో
    0.62
     étape
    0.62
    લિ
    0.61
    ০০০
    0.60
     subsection
    0.59
    Activations Density 0.497%

    No Known Activations