© 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. 14386
    Prev
    Next
    INDEX
    Explanations

    quantities, events, or specific items

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

    advice or verification

    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
    আমর
    0.30
    সমাজ
    0.28
    实用
    0.28
    必要的
    0.28
    নারী
    0.28
    িবাস
    0.27
    基层
    0.27
    楤
    0.27
     মসজিদ
    0.27
    য়ার
    0.26
    POSITIVE LOGITS
     ت
    0.29
     backstory
    0.28
     transcendent
    0.28
     retribution
    0.27
     transcendence
    0.27
    】-
    0.25
    ِل
    0.25
     بُ
    0.25
     selfie
    0.24
     defiant
    0.24
    Activations Density 0.148%

    No Known Activations