© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2306
    Prev
    Next
    INDEX
    Explanations

    back into, back to, back then

    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_9_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
    𝗮
    3.83
    ী
    3.36
    𝗰
    3.27
     squir
    3.08
    е
    3.07
    おります
    3.04
    ów
    2.96
    ?!?
    2.89
    𝗔
    2.87
    ২২
    2.87
    POSITIVE LOGITS
     indietro
    3.49
     forth
    3.25
    gam
    3.11
    诵
    2.93
    noun
    2.90
    lighting
    2.88
    yards
    2.85
    scattering
    2.84
    fired
    2.79
     yönelik
    2.76
    Activations Density 0.196%

    No Known Activations