© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4728
    Prev
    Next
    INDEX
    Explanations

    syndicated columns, products, directions

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

    JSON, list, table, physical

    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
     ફ
    0.50
     বিপরীত
    0.50
    ia
    0.47
    ene
    0.46
    ésus
    0.46
     промежу
    0.45
    éri
    0.44
     deinen
    0.44
    ية
    0.44
    ither
    0.42
    POSITIVE LOGITS
    ش
    0.55
     Jordi
    0.53
     romances
    0.52
     storylines
    0.51
     rumores
    0.51
    ন
    0.51
     gossip
    0.50
    म
    0.49
    하지만
    0.49
    美人
    0.49
    Activations Density 0.000%

    No Known Activations