© 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. 145579
    Prev
    Next
    INDEX
    Explanations

    football, resources, finally

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

    sneaking behind

    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
    قتها
    0.51
    きれい
    0.50
    𝐱
    0.47
    スター
    0.47
    ⏮
    0.46
    ऐप
    0.46
    ()*
    0.45
    ड़ा
    0.45
    हारी
    0.44
     सिंग
    0.43
    POSITIVE LOGITS
     organism
    0.44
     уго
    0.44
    ının
    0.42
    Rés
    0.41
    文件的
    0.40
    俥
    0.40
     Oakland
    0.39
     unofficial
    0.39
     institution
    0.39
     Danielle
    0.39
    Activations Density 0.001%

    No Known Activations