© 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. 123739
    Prev
    Next
    INDEX
    Explanations

    country ballroom

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

    understanding businesses closely related

    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
     달
    0.50
     ga
    0.46
    ීම
    0.46
     endogenous
    0.46
    গাঁও
    0.46
     repellent
    0.46
     föl
    0.45
     sejahtera
    0.44
     følgende
    0.44
     tõ
    0.44
    POSITIVE LOGITS
     Италии
    0.49
    resolved
    0.46
    Ꮸ
    0.45
     уча
    0.44
    茨
    0.44
    των
    0.43
     अनजान
    0.43
    ]=='
    0.43
    motivation
    0.43
     Sabemos
    0.42
    Activations Density 0.000%

    No Known Activations