© 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. 194061
    Prev
    Next
    INDEX
    Explanations

    whether ... common law

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

    app usage

    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
    {|\
    0.53
     andere
    0.51
     allemand
    0.50
     anderes
    0.49
    {.
    0.49
     alkoh
    0.48
     byl
    0.47
     anderen
    0.46
     alkohol
    0.46
    ns
    0.45
    POSITIVE LOGITS
    ээ
    0.52
    არგ
    0.49
    馴染
    0.48
    きた
    0.45
    ждать
    0.45
     पड़ता
    0.45
    鴦
    0.45
    デ
    0.44
    ान्
    0.44
    Џ
    0.44
    Activations Density 0.000%

    No Known Activations