© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 224674
    Prev
    Next
    INDEX
    Explanations

    moon and stars

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

    types and variations

    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
     *
    0.53
    s
    0.52
     can
    0.48
     helpful
    0.48
     complicated
    0.46
     Key
    0.41
     cannot
    0.40
     '
    0.40
     blatantly
    0.40
     부
    0.40
    POSITIVE LOGITS
    agamanam
    0.54
     alterações
    0.53
     extensão
    0.53
     університе
    0.52
     Amazonas
    0.49
    ames
    0.49
    proficiency
    0.47
     علاوہ
    0.47
     cheg
    0.47
    賠
    0.46
    Activations Density 0.001%

    No Known Activations