© 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. 198023
    Prev
    Next
    INDEX
    Explanations

    that number

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

    items following descriptive words

    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
     officially
    0.44
     horseshoe
    0.44
     official
    0.44
     PAG
    0.43
     newsc
    0.43
     ufficial
    0.42
     "
    0.42
     chestnut
    0.42
     concatenated
    0.42
     ​​
    0.41
    POSITIVE LOGITS
     場合
    0.54
     ವೈ
    0.54
    act
    0.50
    acids
    0.50
    お届け
    0.50
     المك
    0.49
     スク
    0.49
    ｻ
    0.49
     Часто
    0.48
    Valid
    0.48
    Activations Density 0.007%

    No Known Activations