© 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. 156718
    Prev
    Next
    INDEX
    Explanations

    must use

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

    attempting tasks or finding value

    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
    رسی
    0.45
    b
    0.45
    ين
    0.44
    тура
    0.44
    लाइ
    0.43
    ConnectionType
    0.42
    имо
    0.40
    闸
    0.40
    这座
    0.39
    IGA
    0.39
    POSITIVE LOGITS
     przede
    0.55
     DETECTION
    0.51
     Pubmed
    0.50
    痕
    0.50
     RECOMMEND
    0.47
     wholeheartedly
    0.47
     πραγμα
    0.47
    tble
    0.46
     inhomogeneities
    0.45
     homog
    0.45
    Activations Density 0.001%

    No Known Activations