© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 6858
    Prev
    Next
    INDEX
    Explanations

    need more info

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     aunque
    0.75
     although
    0.72
    although
    0.68
    虽然
    0.66
     meskipun
    0.66
    雖
    0.66
     deceduto
    0.65
     though
    0.65
     benötigen
    0.65
    虽
    0.65
    POSITIVE LOGITS
     hey
    0.80
     Hey
    0.70
    Hey
    0.68
     Atau
    0.51
    hey
    0.50
    HEY
    0.49
     beggars
    0.48
     ¡
    0.48
     hell
    0.47
     หรือ
    0.46
    Activations Density 0.087%

    No Known Activations