© 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. 27598
    Prev
    Next
    INDEX
    Explanations

    still growing, Still indexes

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

    highly gifted

    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
     这些
    0.49
     פור
    0.46
     మార్
    0.45
    ⏤
    0.45
     THEY
    0.45
    แล้ว
    0.44
    סה
    0.44
    柒
    0.44
    這些
    0.43
     და
    0.43
    POSITIVE LOGITS
     optimistic
    0.54
    乐观
    0.50
    祝い
    0.48
     stomach
    0.47
     optimism
    0.46
     optimist
    0.46
     pessimistic
    0.46
     grapefruit
    0.45
     rejoicing
    0.45
     absurd
    0.44
    Activations Density 0.000%

    No Known Activations