© 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. 134678
    Prev
    Next
    INDEX
    Explanations

    . followed by common words

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

    fields of knowledge

    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
    OURCES
    0.50
     சிகி
    0.49
     шабло
    0.49
     сигнала
    0.48
     tratamientos
    0.48
    ˖
    0.48
    த்ய
    0.48
     адво
    0.48
     冬
    0.47
     गिवन
    0.47
    POSITIVE LOGITS
    ا
    0.46
    ر
    0.46
     Microsoft
    0.45
    ionati
    0.44
    癃
    0.43
     마찬가지
    0.43
     mathemat
    0.42
    agée
    0.41
    นัก
    0.41
     Humphries
    0.41
    Activations Density 0.001%

    No Known Activations