© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65652
    Prev
    Next
    INDEX
    Explanations

    following words or phrases

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

    city renaming

    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
     знания
    0.55
    矨
    0.53
    Ȼ
    0.51
     జ్ఞ
    0.50
     jangka
    0.48
    žno
    0.48
    uları
    0.47
     gne
    0.47
    γο
    0.47
    れた
    0.47
    POSITIVE LOGITS
    0.55
    US
    0.45
    Mid
    0.45
    T
    0.45
    BAR
    0.45
    bitt
    0.44
    ALS
    0.43
    )
    0.43
    Middle
    0.42
    CAN
    0.42
    Activations Density 0.000%

    No Known Activations