© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7960
    Prev
    Next
    INDEX
    Explanations

    how things work or are done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     prosegu
    0.59
    zmdi
    0.58
    𝗗
    0.56
    牪
    0.55
     ይች
    0.55
     étoile
    0.55
     अति
    0.54
     EDIT
    0.54
    [multimodal]
    0.53
     अत्यधिक
    0.53
    POSITIVE LOGITS
     t
    0.56
     관련
    0.53
    నే
    0.52
     tasks
    0.51
     grace
    0.51
    k
    0.50
     lots
    0.50
    wirk
    0.50
    UTO
    0.49
    ത്വ
    0.49
    Activations Density 0.000%

    No Known Activations