© 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. 136897
    Prev
    Next
    INDEX
    Explanations

    versions of

    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
     സ്ഥ
    0.46
    =[]
    0.42
     ಯಾವ
    0.42
    figured
    0.42
    coins
    0.41
    cyclopent
    0.41
    finement
    0.41
    汾
    0.41
     forwarded
    0.41
    efficiency
    0.40
    POSITIVE LOGITS
     toujours
    0.48
     motores
    0.48
    zadeh
    0.44
     berper
    0.43
     jewellery
    0.43
     mogą
    0.42
     moteurs
    0.42
     헤
    0.42
     झेल
    0.41
     neuropsych
    0.41
    Activations Density 0.003%

    No Known Activations