© 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. 148042
    Prev
    Next
    INDEX
    Explanations

    reward centres

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

    common english phrases

    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
    Đây
    0.42
    Diagn
    0.40
    reversed
    0.40
    Diagnosis
    0.39
     ইহা
    0.38
    ♓
    0.38
    YM
    0.38
    atation
    0.38
     еле
    0.38
     pach
    0.38
    POSITIVE LOGITS
    ंकित
    0.47
    सिल
    0.45
    東海
    0.45
    وزيع
    0.45
     dispar
    0.44
     zwischen
    0.44
     Tammy
    0.43
     Nov
    0.43
    ្នុង
    0.43
    焚
    0.43
    Activations Density 0.000%

    No Known Activations