© 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. 16277
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating direction or purpose

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

    formula for combinations

    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
    л
    0.42
    in
    0.40
    or
    0.40
    Innen
    0.40
    Nobody
    0.39
    and
    0.39
    José
    0.38
    밍
    0.38
    presented
    0.38
     Olympi
    0.38
    POSITIVE LOGITS
     decid
    0.50
     créer
    0.48
     mengubah
    0.48
     conexion
    0.48
    ᒐ
    0.47
    ILD
    0.46
     creando
    0.46
     chaîne
    0.46
     confertim
    0.45
     barat
    0.45
    Activations Density 0.001%

    No Known Activations