© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205244
    Prev
    Next
    INDEX
    Explanations

    tahu ! ”

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ول
    0.48
    ጅም
    0.46
    美
    0.46
    ৈ
    0.43
    早餐
    0.42
    採用
    0.42
    糖尿病
    0.41
    ូន
    0.41
    เก็บ
    0.41
     polymer
    0.40
    POSITIVE LOGITS
     tahu
    0.48
    !”
    0.46
    ҳ
    0.45
     khususnya
    0.44
     necesit
    0.43
    IAS
    0.42
    lanan
    0.42
     takut
    0.41
    bung
    0.41
    ?”
    0.40
    Activations Density 0.008%

    No Known Activations