© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4978
    Prev
    Next
    INDEX
    Explanations

    sentence numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mindfulness
    1.17
    زه
    1.14
     ダイヤ
    1.14
     декла
    1.14
    ³,
    1.12
     DISCLAIM
    1.11
     Kard
    1.11
     Delegation
    1.10
    Grat
    1.08
     Mindfulness
    1.06
    POSITIVE LOGITS
    or
    1.09
    ---------
    1.04
    ----------
    1.04
     necesariamente
    1.03
    
    1.03
     musi
    1.02
    ilever
    0.99
     postérieur
    0.99
    icier
    0.98
     noirâtres
    0.98
    Activations Density 0.041%

    No Known Activations