© 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. 1757
    Prev
    Next
    INDEX
    Explanations

    `too` followed by descriptor

    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
    ่
    2.05
    voorbeeld
    1.78
     denn
    1.66
    pc
    1.64
     Ender
    1.63
    9
    1.63
    7
    1.63
    ्स
    1.59
    ্ট
    1.57
    ২৮
    1.57
    POSITIVE LOGITS
    Также
    1.89
    너무
    1.80
    ة
    1.66
    𝐏
    1.59
    过于
    1.57
    Π
    1.48
     Recuer
    1.46
     Podemos
    1.45
    Рабо
    1.43
    এ
    1.38
    Activations Density 0.206%

    No Known Activations