© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 126981
    Prev
    Next
    INDEX
    Explanations

    treatment before ovulation

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

    words with follow-up punctuation

    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
    ᴙ
    0.50
     reckons
    0.46
    推出的
    0.45
     রাস্তায়
    0.43
     Trời
    0.43
     групи
    0.42
     alpin
    0.42
     اٹھ
    0.42
     suic
    0.42
     靴
    0.42
    POSITIVE LOGITS
    tons
    0.55
    kaw
    0.53
    tains
    0.52
    лень
    0.52
    toa
    0.51
    kip
    0.49
    kum
    0.49
    separable
    0.48
    тан
    0.47
    tare
    0.47
    Activations Density 0.001%

    No Known Activations