© 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. 13213
    Prev
    Next
    INDEX
    Explanations

    titles and proper nouns

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

    website names and organizations

    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
    hattim
    0.36
    證據
    0.35
     vardır
    0.34
     senhores
    0.34
    ᱙
    0.34
     AppMethodBeat
    0.34
    道府県
    0.33
    assaytype
    0.33
    餚
    0.33
    㽡
    0.33
    POSITIVE LOGITS
     S
    0.53
     R
    0.51
     J
    0.50
     P
    0.50
     E
    0.49
     D
    0.49
     the
    0.48
     Z
    0.48
     K
    0.48
     A
    0.48
    Activations Density 0.320%

    No Known Activations