© 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. 227318
    Prev
    Next
    INDEX
    Explanations

    pineapple and pronouns

    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
    感謝
    0.45
    坦
    0.44
    חר
    0.43
    }/
    0.40
    ܸ
    0.40
    تر
    0.40
    гістра
    0.40
    сные
    0.40
    𝟎
    0.40
    𝟖
    0.40
    POSITIVE LOGITS
     يكون
    0.65
     subdivided
    0.48
     amass
    0.48
     být
    0.46
     être
    0.46
     tiempo
    0.45
     específ
    0.45
    势力
    0.45
     sial
    0.45
     време
    0.45
    Activations Density 0.001%

    No Known Activations