© 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. 147400
    Prev
    Next
    INDEX
    Explanations

    considering why

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

    Safety, training, and guidelines

    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
    碛
    0.50
     Dubai
    0.49
     दुबई
    0.48
     weist
    0.48
     pietra
    0.48
     Tonga
    0.47
     Emirati
    0.47
    𝙞
    0.47
    ajemen
    0.46
     ні
    0.46
    POSITIVE LOGITS
     inefficient
    0.46
     helps
    0.44
     enlist
    0.44
    getTarget
    0.42
     новой
    0.42
     допо
    0.42
     troubles
    0.42
     recovers
    0.41
     الدوره
    0.41
     getType
    0.41
    Activations Density 0.000%

    No Known Activations