© 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. 104609
    Prev
    Next
    INDEX
    Explanations

    specific word pairs

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

    Intent, Business Model, Good

    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
     賞
    0.53
    *
    0.48
    埃
    0.45
    v
    0.43
    oz
    0.43
    gb
    0.43
     строи
    0.42
    på
    0.41
    、“
    0.40
    gif
    0.40
    POSITIVE LOGITS
     vaginale
    0.48
    쏴
    0.47
     basın
    0.46
    istently
    0.45
     yarı
    0.45
     definisi
    0.45
    ির্ব
    0.45
     lastly
    0.44
     endlich
    0.44
     Finalmente
    0.44
    Activations Density 0.000%

    No Known Activations