© 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. 123172
    Prev
    Next
    INDEX
    Explanations

    asked what

    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
     Frequently
    0.43
     fréquemment
    0.42
    丧
    0.42
     or
    0.40
     fréquente
    0.40
     Drapeau
    0.40
    剂
    0.40
     Physi
    0.39
     conseguir
    0.39
     &
    0.37
    POSITIVE LOGITS
     second
    0.51
     fifth
    0.50
    estrutura
    0.48
     eurozone
    0.47
     seconda
    0.47
     seventh
    0.47
     sixth
    0.46
    риев
    0.46
    രിച്ച
    0.46
    ayah
    0.45
    Activations Density 0.002%

    No Known Activations