© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1964
    Prev
    Next
    INDEX
    Explanations

    technical discussions and disclaimers

    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_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
     denoted
    1.14
     composed
    1.00
     however
    0.99
     correct
    0.98
     produced
    0.92
     any
    0.92
     “
    0.91
     [
    0.90
     encoded
    0.90
     each
    0.90
    POSITIVE LOGITS
    sonaro
    0.97
    objectif
    0.96
    pportunities
    0.94
    ppone
    0.94
    endlich
    0.94
    relativistic
    0.93
    beek
    0.91
    Hlav
    0.91
    <unused70>
    0.90
    Municipal
    0.89
    Activations Density 0.276%

    No Known Activations