© 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. 73662
    Prev
    Next
    INDEX
    Explanations

    to always

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

    time, team, simple, translates, too

    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
    🎙
    0.47
    :\
    0.46
     toured
    0.44
    聲音
    0.44
    :
    0.44
     resonated
    0.43
    Legisl
    0.42
     complied
    0.42
    Voices
    0.42
    ,
    0.42
    POSITIVE LOGITS
    そのような
    0.47
     ഒഴിവാ
    0.46
     malfunctions
    0.46
     parameterType
    0.45
     Indicate
    0.44
     อย่า
    0.44
     arbor
    0.44
     exaggerate
    0.44
    ガール
    0.43
     Confusion
    0.42
    Activations Density 0.001%

    No Known Activations