© 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. 190048
    Prev
    Next
    INDEX
    Explanations

    corporation, Start, results

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

    hidden notes

    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
    ബാ
    0.46
    حب
    0.46
    á
    0.45
    חק
    0.43
    ƌ
    0.43
    ायती
    0.42
    _$
    0.41
    ó
    0.41
    hack
    0.40
     هڪ
    0.40
    POSITIVE LOGITS
     dbcontext
    0.49
     церкви
    0.47
     پیام
    0.46
    Ꮹ
    0.46
     নবী
    0.46
     मुआव
    0.45
     شیع
    0.45
    श्य
    0.44
     সাইফুল
    0.44
     صبر
    0.43
    Activations Density 0.000%

    No Known Activations