© 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. 95382
    Prev
    Next
    INDEX
    Explanations

    whether you

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

    day backup Be Decl Total

    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
     eels
    0.49
    p
    0.47
     Panama
    0.45
    Ста
    0.45
     mouths
    0.44
     understanding
    0.44
    К
    0.43
    papa
    0.43
     pared
    0.42
    Pakistan
    0.42
    POSITIVE LOGITS
     ማለት
    0.53
     ឬ
    0.51
    ๊ะ
    0.50
     sıra
    0.49
     مضمون
    0.48
     مهر
    0.48
     或者
    0.47
     سزا
    0.47
    ürdig
    0.47
     होने
    0.47
    Activations Density 0.001%

    No Known Activations