© 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. 27173
    Prev
    Next
    INDEX
    Explanations

    free, and confidential

    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
    രക്ഷ
    0.42
    谪
    0.40
     ঢুকে
    0.40
    ങ്ങളും
    0.40
    铤
    0.39
     absolv
    0.38
     /,
    0.38
     -,
    0.36
    Շ
    0.36
     તથા
    0.36
    POSITIVE LOGITS
     গী
    0.44
     exposureButton
    0.42
    ヒ
    0.38
    អារ
    0.38
     বনে
    0.37
     fillColorSpace
    0.35
    ৩৯
    0.35
     crystallization
    0.35
     bury
    0.35
     kil
    0.34
    Activations Density 0.086%

    No Known Activations