© 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. 102645
    Prev
    Next
    INDEX
    Explanations

    Regarding

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

    explaining *why* or *how*

    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
     المسؤول
    0.46
    aS
    0.45
    cev
    0.45
    anshi
    0.45
    ⋱
    0.43
    یکم
    0.42
     مسؤول
    0.41
     Éd
    0.41
     Dispersion
    0.41
    rion
    0.40
    POSITIVE LOGITS
    লাষ
    0.44
    看起来
    0.44
     молоды
    0.44
    ਤੇ
    0.43
    看起來
    0.43
    湁
    0.42
     પે
    0.42
    ape
    0.41
    ецца
    0.41
    osaurus
    0.41
    Activations Density 0.001%

    No Known Activations