© 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. 156025
    Prev
    Next
    INDEX
    Explanations

    inventions and life events

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

    unanswerable questions, honestly

    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
     Should
    0.50
     Never
    0.45
    흐
    0.45
     Takes
    0.43
     Enables
    0.42
     জীববিজ্ঞান
    0.41
     razie
    0.40
    тров
    0.40
     Hooker
    0.40
     Narrative
    0.40
    POSITIVE LOGITS
    ţ
    0.51
    embangunan
    0.48
    ಈ
    0.45
    lač
    0.45
     đươ
    0.45
    ijiet
    0.45
     Yal
    0.44
    emal
    0.44
    ţi
    0.43
     tatto
    0.42
    Activations Density 0.003%

    No Known Activations