© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83974
    Prev
    Next
    INDEX
    Explanations

    Lake Tahoe, Sierra Nevada, Battlestar Galactica

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enseignement
    0.43
    חות
    0.39
     春
    0.37
    šće
    0.37
    𒌝
    0.37
     seasonal
    0.37
     Kuro
    0.37
    Skull
    0.37
     کنکریاں
    0.36
    ტი
    0.36
    POSITIVE LOGITS
     BERN
    0.42
    Registered
    0.38
    点击
    0.37
     councils
    0.36
    ichever
    0.35
    該当
    0.35
    菸
    0.35
    Founded
    0.34
    ភេទ
    0.34
    ogenies
    0.33
    Activations Density 0.003%

    No Known Activations