© 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. 244149
    Prev
    Next
    INDEX
    Explanations

    universecork

    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
     agile
    0.49
     morphologies
    0.45
    قع
    0.45
     fechas
    0.44
     espaces
    0.44
    u
    0.41
    1
    0.41
    oder
    0.41
     chairs
    0.41
     polygon
    0.40
    POSITIVE LOGITS
    żenie
    0.48
     జా
    0.47
     weaken
    0.45
     lark
    0.45
     deser
    0.45
     Irina
    0.44
     societ
    0.43
    𝘀
    0.43
    𝗱
    0.43
     mogę
    0.42
    Activations Density 0.000%

    No Known Activations