© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221251
    Prev
    Next
    INDEX
    Explanations

    tax assets, objection contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    Eldrin, Elara, Leo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     semilla
    0.48
     banner
    0.46
    "]},
    0.45
    ),]),
    0.44
     বিখ্যাত
    0.43
     bâtiment
    0.43
     seedlings
    0.42
     earthen
    0.42
     progetto
    0.42
    动脉
    0.41
    POSITIVE LOGITS
    sele
    0.50
    えない
    0.47
    sexual
    0.45
    semer
    0.45
     अनावश्यक
    0.43
    seven
    0.43
    selection
    0.43
    懲
    0.43
     دہ
    0.43
    non
    0.43
    Activations Density 0.000%

    No Known Activations