© 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. 66913
    Prev
    Next
    INDEX
    Explanations

    Apple Store, toString(), traditional players

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

    describing situations and actions

    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
    دیا
    0.47
    Rip
    0.43
    ０
    0.43
    妘
    0.43
    اك
    0.43
    یات
    0.43
    Ben
    0.42
    డా
    0.41
    ی
    0.41
    付けて
    0.40
    POSITIVE LOGITS
     न्यूयॉर्क
    0.54
     Michigan
    0.50
    uš
    0.47
    ḩ
    0.46
    miş
    0.45
     estudar
    0.45
     Antique
    0.44
    cido
    0.44
     i
    0.43
     antique
    0.43
    Activations Density 0.000%

    No Known Activations