© 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. 142972
    Prev
    Next
    INDEX
    Explanations

    less customization

    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
     delirium
    0.47
     مثلا
    0.47
    ؟!
    0.45
    рија
    0.44
    ｧ
    0.44
    انہوں
    0.44
    早在
    0.43
    [],
    0.43
     മൊ
    0.42
     fata
    0.42
    POSITIVE LOGITS
    Opacity
    0.51
    Eth
    0.48
    alphabet
    0.44
    狗
    0.44
    Envelope
    0.43
     கடி
    0.43
    Personal
    0.42
    Control
    0.42
    Ethyl
    0.42
    For
    0.42
    Activations Density 0.002%

    No Known Activations