© 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. 74755
    Prev
    Next
    INDEX
    Explanations

    Home, Kitchen, Computers, Brake, Rear

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

    amazon product pages

    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
    umls
    0.52
    젹
    0.48
     యొక్క
    0.46
     결과
    0.45
    irne
    0.44
    ındaki
    0.44
     வேகமாக
    0.44
    preceq
    0.44
    녠
    0.44
     лише
    0.43
    POSITIVE LOGITS
     বলল
    0.40
     pernah
    0.40
    徳
    0.39
     کن
    0.39
     acoustics
    0.38
     Very
    0.38
     Had
    0.38
     proving
    0.38
     Nagpur
    0.37
     escribió
    0.37
    Activations Density 0.002%

    No Known Activations