© 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. 96554
    Prev
    Next
    INDEX
    Explanations

    freedoms and interests

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

    scaling group, several books, cartoon cups, privacy push

    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
     about
    0.54
    about
    0.52
     Justin
    0.50
     आला
    0.49
    o
    0.49
     June
    0.48
    斻
    0.48
     Alpine
    0.48
     Andean
    0.47
     Andrea
    0.46
    POSITIVE LOGITS
     vucc
    0.48
     করুক
    0.47
    withtag
    0.47
     zewnętr
    0.46
    грамма
    0.45
     крово
    0.45
    Pepper
    0.45
     সার্ভ
    0.45
     الخارجية
    0.45
    ѫ
    0.44
    Activations Density 0.001%

    No Known Activations