© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    origin of specific words

    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_16k_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
    ≲
    0.44
     compris
    0.44
     Photographic
    0.43
     góc
    0.43
     networked
    0.43
     mre
    0.43
    ्वल
    0.42
     कमी
    0.42
     climbed
    0.42
     pati
    0.41
    POSITIVE LOGITS
     bestimmte
    0.46
    erer
    0.46
    哈
    0.44
    usahaan
    0.44
     ਮੰ
    0.43
     instance
    0.42
    ahul
    0.42
    iciones
    0.42
    azienda
    0.42
     ilyen
    0.42
    Activations Density 0.027%

    No Known Activations