© 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. 106260
    Prev
    Next
    INDEX
    Explanations

    theatre, protect, way, used, male

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

    multilingual content identification

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ’:
    0.50
     pośred
    0.49
     excepted
    0.48
     eux
    0.47
     Dedicated
    0.47
    枉
    0.45
    :`
    0.44
     direct
    0.44
     Direct
    0.44
     inspir
    0.44
    POSITIVE LOGITS
     З
    0.45
    ind
    0.45
     kelas
    0.41
    CLASSES
    0.41
     হয়েছে
    0.41
     विशाल
    0.41
     indeterminate
    0.40
     அடையாள
    0.40
     стало
    0.40
    кло
    0.40
    Activations Density 0.000%

    No Known Activations