© 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. 22877
    Prev
    Next
    INDEX
    Explanations

    phrase or specific words

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

    string object manipulation

    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
     chunkSize
    0.49
     дети
    0.47
     Bue
    0.46
     Samu
    0.46
     hir
    0.45
     menino
    0.45
    מ
    0.45
     كر
    0.44
    ات
    0.44
     Hir
    0.44
    POSITIVE LOGITS
    anstalt
    0.47
     vinegar
    0.46
    idyl
    0.45
    plist
    0.45
    timed
    0.45
    vascular
    0.44
     दिश
    0.44
     Сасик
    0.44
    nueva
    0.43
    ζο
    0.43
    Activations Density 0.000%

    No Known Activations