© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24932
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic operations

    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_all/layer_41_width_262k_l0_big
    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
    <unused971>
    0.47
     použí
    0.47
    <unused307>
    0.45
    <unused336>
    0.44
    <unused317>
    0.43
    Storia
    0.43
    ່
    0.43
    ជា
    0.43
     traditionnelle
    0.43
    <unused2049>
    0.43
    POSITIVE LOGITS
     five
    0.67
     seven
    0.67
    5
    0.67
     $
    0.66
    6
    0.65
     six
    0.64
     eight
    0.63
     four
    0.62
     sixty
    0.62
    7
    0.62
    Activations Density 0.194%

    No Known Activations