© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30940
    Prev
    Next
    INDEX
    Explanations

    collocations and word completions

    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
     roślin
    0.46
     shinobi
    0.44
    呈现
    0.43
     naszym
    0.43
     chocolat
    0.43
    萄
    0.43
    樱
    0.43
     ainfi
    0.43
    始终
    0.42
    钮
    0.42
    POSITIVE LOGITS
    da
    0.69
    ma
    0.56
    len
    0.55
    den
    0.54
    gen
    0.54
    ren
    0.53
    enheim
    0.53
    ton
    0.52
    kten
    0.50
    micro
    0.50
    Activations Density 0.001%

    No Known Activations