© 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. 79925
    Prev
    Next
    INDEX
    Explanations

    Geographical locations

    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
    oh
    0.54
    edad
    0.51
    er
    0.50
    ed
    0.50
    pa
    0.47
    M
    0.47
    ah
    0.46
    AR
    0.46
    OM
    0.46
    UN
    0.46
    POSITIVE LOGITS
     Adviser
    0.51
     Fonbet
    0.46
     Allentown
    0.44
    सबुक
    0.43
     puppets
    0.43
     সক্র
    0.43
     focussing
    0.43
     Hewitt
    0.43
     fielded
    0.43
     hearers
    0.43
    Activations Density 0.001%

    No Known Activations