© 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. 205186
    Prev
    Next
    INDEX
    Explanations

    hereby warrant

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

    added, creation, heating, pretty

    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
     Sensor
    0.42
     originales
    0.41
    ధ
    0.41
    гот
    0.40
    ​,
    0.39
    ીર
    0.39
     maximizes
    0.39
     champions
    0.39
     killers
    0.39
     ఉంటాయి
    0.39
    POSITIVE LOGITS
    Pretty
    0.49
    １
    0.47
    :.
    0.46
    THERE
    0.45
    もう
    0.44
    .°
    0.43
    ."'
    0.43
    ..
    0.42
    Notable
    0.42
    Others
    0.42
    Activations Density 0.001%

    No Known Activations