© 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. 48482
    Prev
    Next
    INDEX
    Explanations

    referring to specific terms

    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
    لوب
    0.51
    Auch
    0.46
    হৃত
    0.46
    iled
    0.45
    Produto
    0.44
    etten
    0.44
    Architect
    0.44
    眹
    0.43
    Suit
    0.43
     sian
    0.43
    POSITIVE LOGITS
     in
    0.48
     abstinence
    0.48
    ¦
    0.46
     Saccharomyces
    0.46
    ヤマハ
    0.46
     Conjecture
    0.45
     cessation
    0.45
     chu
    0.44
    e
    0.44
     NSMutable
    0.44
    Activations Density 0.005%

    No Known Activations