© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14358
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and punctuation

    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_65k_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
    셸
    0.57
    ों
    0.49
    ޏ
    0.47
     здания
    0.46
    (−
    0.44
    readlines
    0.43
     gmin
    0.43
    तिर
    0.43
    Buildings
    0.42
     એલ
    0.42
    POSITIVE LOGITS
     crafted
    0.46
    S
    0.46
     مهما
    0.44
    Q
    0.44
     手
    0.43
     creato
    0.43
     offering
    0.42
     அதிகரித்து
    0.42
    e
    0.42
    orada
    0.41
    Activations Density 0.004%

    No Known Activations