© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90229
    Prev
    Next
    INDEX
    Explanations

    technical terms and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.47
     Relating
    0.47
    و
    0.45
     Arithmetic
    0.44
     Frequency
    0.42
     Fruit
    0.41
    ประมาณ
    0.41
     Concerned
    0.40
    unicode
    0.40
     pronouncing
    0.40
    POSITIVE LOGITS
    ではない
    0.50
     pozw
    0.50
     biosphere
    0.49
     bukanlah
    0.47
    はもちろん
    0.47
    tel
    0.46
     vean
    0.46
     ކ
    0.45
    یە
    0.44
    Tel
    0.44
    Activations Density 0.001%

    No Known Activations