© 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. 87574
    Prev
    Next
    INDEX
    Explanations

    links to

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

    underrated, undervalued, underhyped

    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
    的话
    0.44
     trung
    0.43
     taal
    0.42
    ꯔ
    0.41
    特典
    0.41
     scratching
    0.41
     rối
    0.40
     Burroughs
    0.40
    ی
    0.40
     coherent
    0.40
    POSITIVE LOGITS
     republik
    0.51
    orten
    0.47
    march
    0.46
     democracies
    0.46
    dic
    0.46
    policies
    0.46
     республи
    0.45
    et
    0.45
    pandemic
    0.45
    editors
    0.45
    Activations Density 0.001%

    No Known Activations