© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4607
    Prev
    Next
    INDEX
    Explanations

    negative intensity

    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_12_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
    i
    1.15
    n
    1.10
    em
    1.09
    ano
    1.06
    nq
    1.04
    a
    1.02
     (
    1.01
     самому
    1.00
    pt
    1.00
     взрослых
    0.96
    POSITIVE LOGITS
     grueling
    1.05
     grasped
    1.02
     edgy
    1.00
    )}$,
    0.99
     fortunes
    0.99
    ҝ
    0.98
    ﾌ
    0.96
    ों
    0.96
     fief
    0.95
    鉆
    0.95
    Activations Density 0.153%

    No Known Activations