© 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-65K
    7. 62359
    Prev
    Next
    INDEX
    Explanations

    . followed by a capital letter

    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_65k_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
    Toolbar
    0.47
     кантип
    0.46
    Mama
    0.44
    如何
    0.44
    Dict
    0.44
    Whatsapp
    0.43
    哴
    0.42
    剷
    0.42
    тике
    0.41
    ྭ
    0.41
    POSITIVE LOGITS
     for
    0.53
     sowohl
    0.53
     jeweils
    0.48
     regarding
    0.47
     ※
    0.46
     marcos
    0.46
     Ei
    0.45
     Ein
    0.45
     city
    0.44
     Reis
    0.44
    Activations Density 0.008%

    No Known Activations