© 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. 126783
    Prev
    Next
    INDEX
    Explanations

    surroundings from

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

    documentation, review, exam, surface preparation

    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
    oxane
    0.48
    Encyclopedia
    0.46
    莊
    0.46
    binoculars
    0.45
    opo
    0.45
    ೋಪ
    0.44
    ორე
    0.44
    Ω
    0.44
    andra
    0.44
     जर्नल
    0.44
    POSITIVE LOGITS
    wirken
    0.52
     جنہوں
    0.43
     llevaba
    0.42
     тощо
    0.42
     scored
    0.40
     zetten
    0.40
     крити
    0.40
     highest
    0.39
     teamwork
    0.39
     vừa
    0.38
    Activations Density 0.002%

    No Known Activations