© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136960
    Prev
    Next
    INDEX
    Explanations

    cities, places, classical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aidant
    0.50
    א
    0.50
    中有
    0.50
    opération
    0.48
     membantu
    0.47
    Little
    0.46
    Os
    0.45
    C
    0.45
    ुट
    0.45
     کمی
    0.45
    POSITIVE LOGITS
     flares
    0.57
     cities
    0.51
     его
    0.49
     ciudades
    0.48
     densely
    0.47
    italizationType
    0.46
    n
    0.45
     exclude
    0.45
     classically
    0.44
     steels
    0.44
    Activations Density 0.000%

    No Known Activations