© 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. 121679
    Prev
    Next
    INDEX
    Explanations

    since one, original packaging, Mondays and

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

    even followed by context

    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
     ပဲ
    0.54
     αποτε
    0.49
    DateField
    0.46
     allevi
    0.46
    xtures
    0.44
     पाण्या
    0.43
     মহাশয়
    0.43
    瞽
    0.43
    ч
    0.42
    aceutical
    0.42
    POSITIVE LOGITS
     git
    0.52
    tip
    0.47
    kel
    0.45
     docs
    0.44
     gah
    0.44
     gk
    0.44
     stents
    0.43
     zs
    0.43
     discriminated
    0.43
     gini
    0.43
    Activations Density 0.000%

    No Known Activations