© 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. 53-GEMMASCOPE-2-RES-262K
    7. 38267
    Prev
    Next
    INDEX
    Explanations

    alliteration and consonants

    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_53_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
     character
    0.46
     Character
    0.46
     karakter
    0.41
     Charakter
    0.38
     cany
    0.38
     তা
    0.38
     ё
    0.37
     Ё
    0.37
     teken
    0.37
     indefin
    0.37
    POSITIVE LOGITS
     consonant
    0.88
     consonants
    0.87
    Cons
    0.73
     kons
    0.71
     conson
    0.71
     cons
    0.68
     Cons
    0.64
    ass
    0.59
     Kons
    0.57
     ass
    0.55
    Activations Density 0.012%

    No Known Activations