© 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. 164038
    Prev
    Next
    INDEX
    Explanations

    heavyweight boxer, cheesecake, harmless radio

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

    comprehensive evaluation; thorough explanation

    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
     But
    0.52
     entw
    0.52
     Liu
    0.49
     "
    0.48
     Wild
    0.48
     Peck
    0.47
     Gallo
    0.47
    !",
    0.47
     Brend
    0.46
    ie
    0.46
    POSITIVE LOGITS
    lmfit
    0.55
    muestra
    0.54
    حدد
    0.51
    ﻛ
    0.50
    そらく
    0.49
    темати
    0.48
    sortie
    0.48
    ޕ
    0.47
     راجس
    0.47
    ឧបករណ៍
    0.47
    Activations Density 0.001%

    No Known Activations