© 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. 171857
    Prev
    Next
    INDEX
    Explanations

    rental stress, rock, until RNA, value and, animals that, disclosure of

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

    conditions and dependencies

    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
    欄
    0.46
     telenov
    0.46
     enig
    0.46
     sages
    0.44
     onlookers
    0.44
    erun
    0.43
     usw
    0.40
    guests
    0.39
    狎
    0.39
    rimos
    0.39
    POSITIVE LOGITS
     synthesized
    0.43
     চাওয়া
    0.43
     मोल
    0.43
     कास्ट
    0.41
     آتا
    0.41
    condition
    0.40
     conditioner
    0.40
    characterized
    0.40
    il
    0.40
    лоти
    0.40
    Activations Density 0.000%

    No Known Activations