© 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-262K
    7. 203386
    Prev
    Next
    INDEX
    Explanations

    what if you could

    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
    се
    0.48
    鋆
    0.48
    Ι
    0.47
    Hive
    0.45
    нали
    0.44
    Ante
    0.43
    І
    0.43
    ี
    0.42
    Дан
    0.42
    ペ
    0.42
    POSITIVE LOGITS
     truc
    0.45
     assembler
    0.42
     angezeigt
    0.41
     mêmes
    0.41
     မှာ
    0.40
    izei
    0.39
     aime
    0.39
     participantes
    0.39
    人了
    0.39
     airports
    0.38
    Activations Density 0.002%

    No Known Activations