© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63102
    Prev
    Next
    INDEX
    Explanations

    utf8 encoding and language handling

    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
     וב
    0.43
     R
    0.40
     SCRE
    0.39
    isu
    0.39
    STRAL
    0.39
    ITING
    0.39
    şti
    0.38
    anye
    0.38
     K
    0.38
    ّر
    0.37
    POSITIVE LOGITS
     demikian
    0.50
     utilización
    0.44
     забезпечення
    0.41
     peł
    0.39
     якщо
    0.38
     linearly
    0.37
    CQL
    0.37
     persönlichen
    0.37
     fives
    0.37
     использованием
    0.36
    Activations Density 0.002%

    No Known Activations