© 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. 198555
    Prev
    Next
    INDEX
    Explanations

    Mars Science, measurable design

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

    designations and possibilities

    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
    乌
    0.48
    at
    0.45
    ly
    0.44
    <0xF0>
    0.42
    aire
    0.41
    us
    0.40
    у
    0.40
    อ
    0.40
     recesses
    0.40
    н
    0.40
    POSITIVE LOGITS
     denominada
    0.50
     વખત
    0.50
     അടി
    0.49
     cachorro
    0.49
     유엔
    0.48
    ਿਹ
    0.48
     transformada
    0.48
     chamada
    0.47
     prak
    0.46
     作り
    0.46
    Activations Density 0.000%

    No Known Activations