© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167869
    Prev
    Next
    INDEX
    Explanations

    descriptions of origins or appearance

    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_40_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
    isselle
    0.46
     Тыва
    0.44
    ttet
    0.41
    豪
    0.41
    徝
    0.40
     minimally
    0.39
     غ
    0.38
    ጣ
    0.38
    Scala
    0.38
    ueda
    0.38
    POSITIVE LOGITS
     triplets
    0.43
     PUB
    0.42
     KAP
    0.42
     osnov
    0.41
     kap
    0.40
     rok
    0.40
    ān
    0.39
     uj
    0.39
    Ნ
    0.38
     PROBLEMS
    0.38
    Activations Density 0.002%

    No Known Activations