© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1338
    Prev
    Next
    INDEX
    Explanations

    insisted or mentioned

    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_all/layer_41_width_262k_l0_big
    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
     จึง
    0.52
    ោង
    0.48
     وګ
    0.46
     シンプル
    0.46
    𝑜
    0.45
    ╁
    0.44
     বৃহত্তম
    0.43
    ᾗ
    0.42
    ollipop
    0.41
    ั่ว
    0.41
    POSITIVE LOGITS
     insist
    1.13
     insisting
    1.02
     insisted
    0.99
     insists
    0.96
     told
    0.86
     insistent
    0.84
     insistence
    0.83
     complains
    0.81
     mention
    0.79
     complained
    0.78
    Activations Density 0.003%

    No Known Activations