© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116145
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    garlic, rosemary, soap, latch

    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
    ad
    0.53
    ver
    0.51
    LR
    0.50
    varian
    0.50
    virus
    0.49
    the
    0.48
    verse
    0.48
    í
    0.48
     Ashland
    0.47
    err
    0.47
    POSITIVE LOGITS
     artık
    0.55
     öğretmen
    0.52
     nouveaux
    0.50
     கல்
    0.50
     gespe
    0.50
     peux
    0.49
     சிறு
    0.48
     deux
    0.48
     તેઓ
    0.48
     δύο
    0.47
    Activations Density 0.000%

    No Known Activations