© 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. 177907
    Prev
    Next
    INDEX
    Explanations

    stand, local, outfits, personal, tiny, lumping, stuffing

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

    poems and debates

    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
     N
    0.48
    тная
    0.47
    ale
    0.46
     hiszen
    0.46
     Leo
    0.45
    utt
    0.45
    idan
    0.45
    ्ल
    0.44
     Strugg
    0.44
    वरणीय
    0.44
    POSITIVE LOGITS
    бер
    0.46
    敺
    0.46
    节日
    0.45
    闂
    0.45
     beauté
    0.44
    muse
    0.43
     fraudsters
    0.43
     பை
    0.43
     الحم
    0.43
    ኑ
    0.42
    Activations Density 0.001%

    No Known Activations