© 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. 31969
    Prev
    Next
    INDEX
    Explanations

    phone numbers or locations

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

    how to use

    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
    निवेश
    0.46
     നടത്ത
    0.45
     vVertex
    0.44
    嗎
    0.44
    廁
    0.43
    滩
    0.42
    |$
    0.42
    కార
    0.42
    ̠
    0.41
    河
    0.41
    POSITIVE LOGITS
     mts
    0.51
     ওষুধের
    0.51
     ঘনিষ্ঠভাবে
    0.50
     KBS
    0.50
     trainees
    0.50
     recruits
    0.49
     scanners
    0.48
     advances
    0.48
     grooves
    0.47
     alarms
    0.46
    Activations Density 0.000%

    No Known Activations