© 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. 172785
    Prev
    Next
    INDEX
    Explanations

    specific words following certain tokens

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

    drive letters, paths, or library names

    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
    誼
    0.50
    Cheerful
    0.48
     tubuh
    0.47
    ؟!
    0.46
     saudável
    0.45
     தெரிவித்த
    0.45
     sekaligus
    0.43
    સિંહ
    0.42
     بدن
    0.42
    ંબ
    0.42
    POSITIVE LOGITS
    烝
    0.46
    ąż
    0.46
    пей
    0.42
    因为
    0.40
    rieve
    0.40
    льным
    0.40
    льна
    0.40
    діть
    0.40
     Rely
    0.40
     interrupt
    0.40
    Activations Density 0.001%

    No Known Activations