© 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. 12-GEMMASCOPE-2-RES-16K
    7. 15929
    Prev
    Next
    INDEX
    Explanations

    not always

    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
    t
    1.05
     finalement
    1.04
     cuantos
    1.03
     akong
    1.01
    testid
    1.01
    arrerol
    1.00
     tropomyosin
    0.99
     लागि
    0.99
    リッジ
    0.98
    मौसम
    0.98
    POSITIVE LOGITS
    >
    1.14
     I
    1.12
    Text
    1.12
    Information
    1.03
    Language
    1.02
    Of
    1.02
    I
    1.02
    Not
    1.01
    Opt
    1.01
    Observable
    1.00
    Activations Density 0.333%

    No Known Activations