© 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. 45902
    Prev
    Next
    INDEX
    Explanations

    directly activate

    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
    dS
    0.49
    }}{|
    0.46
    的双
    0.45
    восто
    0.44
     Tjiwarl
    0.44
    凰
    0.43
    сек
    0.43
    岧
    0.42
    прия
    0.41
    和平
    0.41
    POSITIVE LOGITS
     l
    0.58
     creatinine
    0.51
    io
    0.49
    ceedings
    0.49
     superintend
    0.48
     execução
    0.47
     gh
    0.47
     n
    0.46
    adh
    0.45
     brady
    0.45
    Activations Density 0.001%

    No Known Activations