© 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. 44487
    Prev
    Next
    INDEX
    Explanations

    face tone

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

    life arose on earth, fully water-soluble, finding missions, ChatGPT, embraces

    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
    ップ
    0.50
    их
    0.48
    ЛЕ
    0.46
    कायदा
    0.46
     جوړونکي
    0.45
    例えば
    0.45
    PRODUCTION
    0.44
    楶
    0.44
    EtOH
    0.44
    なか
    0.44
    POSITIVE LOGITS
    hasa
    0.50
     cooled
    0.48
    onta
    0.48
    asa
    0.48
    ns
    0.47
     kuris
    0.46
    iedo
    0.46
     ASA
    0.46
    nader
    0.46
    swer
    0.46
    Activations Density 0.000%

    No Known Activations