© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3081
    Prev
    Next
    INDEX
    Explanations

    instructions or statements

    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_24_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
     மற்றும்
    0.72
     və
    0.70
     ও
    0.68
     criança
    0.68
     reduzir
    0.66
     posso
    0.66
     niña
    0.65
     слабы
    0.65
     tolerancia
    0.65
     và
    0.64
    POSITIVE LOGITS
    !
    0.69
    (!)
    0.66
    这种
    0.65
    This
    0.64
    this
    0.64
    S
    0.60
    这一
    0.59
    Yet
    0.59
     unwittingly
    0.59
    Indeed
    0.59
    Activations Density 0.001%

    No Known Activations