© 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. 107849
    Prev
    Next
    INDEX
    Explanations

    AR or compass direction

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

    description of concepts

    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
    Announcement
    0.47
    s
    0.47
    kais
    0.45
    supports
    0.45
    setzung
    0.43
     hiked
    0.43
    supported
    0.42
    in
    0.42
    atribut
    0.42
    mout
    0.42
    POSITIVE LOGITS
    誤差
    0.61
     useRef
    0.46
     mengg
    0.45
    廻
    0.45
     निर्देशा
    0.45
     pravi
    0.43
    徒歩
    0.43
    答え
    0.43
    喩
    0.43
     permiten
    0.42
    Activations Density 0.000%

    No Known Activations