© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 20
    Prev
    Next
    INDEX
    Explanations

    conditions, requirements, or things that exist

    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_17_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
     Gaussian
    0.55
    pseudo
    0.53
    и
    0.47
    Fourier
    0.46
     Boolean
    0.46
    Gaussian
    0.44
    Irr
    0.43
    الي
    0.43
     Fourier
    0.43
    Astronom
    0.43
    POSITIVE LOGITS
     memastikan
    0.73
    .;
    0.70
     ដើម្បី
    0.69
     ebenso
    0.69
     également
    0.68
    .")
    0.67
     prüfen
    0.66
     ខ
    0.64
     alongside
    0.63
     Einwill
    0.63
    Activations Density 1.184%

    No Known Activations