© 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. 54692
    Prev
    Next
    INDEX
    Explanations

    collocations following certain words

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

    types of categories

    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
    ્ર
    0.48
     bloated
    0.46
    ản
    0.45
    事务所
    0.45
    贓
    0.44
    鏖
    0.43
     DOD
    0.42
    ূলক
    0.42
     UHD
    0.42
    TempBuffer
    0.42
    POSITIVE LOGITS
    u
    0.59
    sms
    0.53
     confirm
    0.52
    i
    0.52
    t
    0.50
    trial
    0.50
    other
    0.48
    сколько
    0.48
     কেনার
    0.48
    ⁠
    0.47
    Activations Density 0.000%

    No Known Activations