© 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. 41494
    Prev
    Next
    INDEX
    Explanations

    for experiment, to signify

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

    nuanced, integration, ads, room

    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
     Herbst
    0.43
     القرار
    0.42
     প্রত্যক্ষ
    0.42
     tät
    0.41
     перво
    0.41
    配备
    0.40
    绵
    0.40
     verfügt
    0.40
     employs
    0.39
     Vegetation
    0.39
    POSITIVE LOGITS
    𝗧
    0.43
    ത്തുന്ന
    0.43
     mysteriously
    0.40
    卻
    0.40
    harmed
    0.39
    undered
    0.39
     functionalities
    0.38
     worldly
    0.38
     ≠
    0.38
     rut
    0.38
    Activations Density 0.000%

    No Known Activations