© 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-262K
    7. 199808
    Prev
    Next
    INDEX
    Explanations

    don't exist in English

    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
    ртуа
    0.52
    单
    0.47
     pointless
    0.46
     precluded
    0.44
    ణులు
    0.44
     pesquis
    0.44
    ĕç
    0.44
     sucks
    0.43
     permettre
    0.43
     заниматься
    0.43
    POSITIVE LOGITS
    BorderStyle
    0.42
    \|^
    0.42
     분위
    0.42
     предстоя
    0.41
     атмос
    0.41
    されました
    0.41
     主要
    0.41
     goddesses
    0.40
    Voltage
    0.40
     সর্বপ্রথম
    0.40
    Activations Density 0.001%

    No Known Activations