© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142399
    Prev
    Next
    INDEX
    Explanations

    different language words

    np_acts-logits-general · gemini-2.5-flash-lite

    . or * / E minor / Page and / resulting glacial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quantity
    0.48
    ン
    0.47
     кількість
    0.46
    Gravestone
    0.45
    ْم
    0.45
     patted
    0.45
    no
    0.45
    是多少
    0.44
     no
    0.43
    Reviewed
    0.43
    POSITIVE LOGITS
     Nizam
    0.53
     Nipp
    0.50
    u
    0.50
     বার্ত
    0.49
    ποίη
    0.49
    läge
    0.47
     ungkap
    0.47
     récemment
    0.47
     Fuse
    0.47
     Sport
    0.46
    Activations Density 0.000%

    No Known Activations