© 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. 182505
    Prev
    Next
    INDEX
    Explanations

    unusual tax

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

    multispectral, within, calculate for, friday

    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
     hosp
    0.53
     antiserum
    0.49
     adj
    0.45
    ansom
    0.45
    ospital
    0.44
    ול
    0.44
    ﹍
    0.44
    nl
    0.44
    𝙢
    0.44
    𝙣
    0.44
    POSITIVE LOGITS
     storyteller
    0.47
    とされる
    0.47
     firepower
    0.46
    িক্ষ
    0.44
    zoic
    0.44
    filtering
    0.44
    heastern
    0.43
     ঘণ্টায়
    0.43
    と呼ばれる
    0.42
     ঘণ্টার
    0.42
    Activations Density 0.001%

    No Known Activations