© 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. 23157
    Prev
    Next
    INDEX
    Explanations

    action and progression

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

    her independent user experience

    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
    ק
    0.44
    젠
    0.41
    遢
    0.41
     успех
    0.39
    Ça
    0.39
    𝗣
    0.39
    谩
    0.39
    ча
    0.38
    zął
    0.38
    让人
    0.38
    POSITIVE LOGITS
     independently
    0.36
     ebenfalls
    0.36
     independent
    0.35
     correl
    0.34
     Malt
    0.34
     polypeptides
    0.34
     mimics
    0.34
     Bamberger
    0.34
     deriv
    0.33
     physic
    0.33
    Activations Density 0.026%

    No Known Activations