© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4124
    Prev
    Next
    INDEX
    Explanations

    data collection and privacy concerns

    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
     Fiziki
    0.48
    OLD
    0.47
    ay
    0.46
    enie
    0.45
    ल्डेन
    0.44
    ुलिस
    0.44
    த்தட்ட
    0.44
    踢
    0.44
    ନ୍ତି
    0.43
     Elektrokh
    0.43
    POSITIVE LOGITS
    より
    0.46
     la
    0.44
     panning
    0.43
     pectin
    0.42
     perfection
    0.42
     closer
    0.41
     rel
    0.41
     Jekyll
    0.41
     Sw
    0.41
    佳
    0.41
    Activations Density 0.015%

    No Known Activations