© 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. 218512
    Prev
    Next
    INDEX
    Explanations

    negations and non-support

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

    multilingual context or linguistic style

    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
    ย
    0.52
    ，
    0.49
    uction
    0.49
    emb
    0.48
    у
    0.47
     όταν
    0.46
     मित्रा
    0.46
    mb
    0.46
     enzimas
    0.46
    ocole
    0.46
    POSITIVE LOGITS
     Tidak
    0.44
     Shouldn
    0.44
    Nunca
    0.44
    炤
    0.41
     nejsou
    0.41
    ല്ലാത്ത
    0.41
    :”
    0.40
     nebude
    0.40
    ূন্য
    0.39
    จะไม่
    0.39
    Activations Density 0.000%

    No Known Activations