© 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. 121024
    Prev
    Next
    INDEX
    Explanations

    San Francisco locals

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

    with clarity

    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
     corresponds
    0.45
     Bali
    0.44
     Cannot
    0.43
     carcinomas
    0.43
    }),
    0.42
     correspond
    0.42
     insecticides
    0.42
    queries
    0.41
     Hokkaido
    0.41
     Tokio
    0.41
    POSITIVE LOGITS
    朝着
    0.52
    再一次
    0.50
     הג
    0.45
     رکھیں
    0.45
    礼
    0.44
    Congrats
    0.44
    GPS
    0.43
    PMS
    0.42
     desg
    0.41
    देव
    0.41
    Activations Density 0.001%

    No Known Activations