© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2814
    Prev
    Next
    INDEX
    Explanations

    what you found amazing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     했
    0.39
     supérieures
    0.39
    ேய
    0.38
     dépens
    0.38
    অর্চনা
    0.37
     mediados
    0.35
     dérivés
    0.35
     दिश
    0.35
    вной
    0.35
    விழ
    0.34
    POSITIVE LOGITS
     Tz
    0.44
     BNB
    0.42
     EtOAc
    0.42
    ␣
    0.41
    ‟
    0.41
     Iod
    0.41
     Bz
    0.39
     Tk
    0.39
     Dz
    0.38
     Yesu
    0.38
    Activations Density 3.205%

    No Known Activations