© 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. 164422
    Prev
    Next
    INDEX
    Explanations

    application or rescued application

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

    going viral

    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
     ಕೊಡ
    0.48
    pineapple
    0.47
    籟
    0.45
    簡單
    0.45
    ভ
    0.44
    言葉
    0.43
     SIMPLE
    0.43
    給
    0.43
    pop
    0.42
    表現
    0.42
    POSITIVE LOGITS
     ach
    0.47
     avatar
    0.46
     ant
    0.46
     antica
    0.46
     antigüedad
    0.46
     ont
    0.45
     anthropologist
    0.45
     kampus
    0.44
    以色列
    0.44
     avis
    0.44
    Activations Density 0.001%

    No Known Activations