© 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-TRANSCODER-262K
    7. 30926
    Prev
    Next
    INDEX
    Explanations

    Muhammad last prophet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     partecipazione
    0.39
    မှတ်
    0.37
     Blade
    0.37
     #:
    0.36
     নিচে
    0.36
    indrical
    0.36
     Votes
    0.36
     سیس
    0.36
    গী
    0.35
    ɲ
    0.35
    POSITIVE LOGITS
    峄
    0.44
    枠
    0.38
    Selenium
    0.37
    諾
    0.37
     Sent
    0.36
    sent
    0.35
    都道府県
    0.35
    Sent
    0.35
    Ethn
    0.35
    芗
    0.34
    Activations Density 0.007%

    No Known Activations