© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115890
    Prev
    Next
    INDEX
    Explanations

    designed specifically

    np_acts-logits-general · gemini-2.5-flash-lite

    sequence of actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oxalate
    0.61
     oxalic
    0.51
     empecé
    0.50
     usaha
    0.49
     yakin
    0.47
    ’;
    0.46
    BUGFS
    0.46
     înt
    0.45
     이차
    0.45
     sejak
    0.44
    POSITIVE LOGITS
     يوليو
    0.48
    吳
    0.48
    économ
    0.47
    經濟
    0.45
     مايو
    0.44
    exceptions
    0.43
     ልዩ
    0.43
     مركز
    0.43
    According
    0.42
     Chaud
    0.42
    Activations Density 0.002%

    No Known Activations