© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7903
    Prev
    Next
    INDEX
    Explanations

    RAINN National Network

    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_31_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
     –
    0.56
    haha
    0.54
    Ⲕ
    0.54
    unk
    0.54
    lol
    0.52
    rose
    0.49
    v
    0.49
    trans
    0.49
    ℞
    0.49
    –
    0.48
    POSITIVE LOGITS
     serta
    0.63
     nonché
    0.62
    xcodep
    0.57
     그리고
    0.54
    estamps
    0.53
     እንዲሁም
    0.53
     Yama
    0.53
    ontiti
    0.53
     मह
    0.53
     wèi
    0.53
    Activations Density 0.052%

    No Known Activations