© 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. 16-GEMMASCOPE-2-RES-262K
    7. 89583
    Prev
    Next
    INDEX
    Explanations

    befriended ending

    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_16_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
     archiv
    0.54
    ஜெ
    0.53
     agacch
    0.52
    rš
    0.48
    arlı
    0.48
     appellate
    0.46
    쿠
    0.46
    abbanti
    0.44
    lük
    0.43
    이브
    0.43
    POSITIVE LOGITS
    1
    0.56
     trotz
    0.52
     दिन
    0.51
     Malgré
    0.50
    2
    0.50
     About
    0.49
    freq
    0.49
     Months
    0.48
    About
    0.48
     Tou
    0.47
    Activations Density 0.000%

    No Known Activations