© 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. 16-GEMMASCOPE-2-RES-262K
    7. 87850
    Prev
    Next
    INDEX
    Explanations

    is it

    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
    ාවේ
    0.67
     caractères
    0.63
    ７
    0.61
     வளர்ச்ச
    0.61
    ﻒ
    0.61
    േഷ്
    0.59
    am
    0.59
     avvi
    0.59
    ｇ
    0.59
    ｋ
    0.59
    POSITIVE LOGITS
    nell
    0.61
     ו
    0.60
     commute
    0.59
     exertion
    0.57
     and
    0.57
     honestly
    0.55
    x
    0.55
    nel
    0.54
     .
    0.53
    תה
    0.53
    Activations Density 0.001%

    No Known Activations