© 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. 153906
    Prev
    Next
    INDEX
    Explanations

    commercial announcements and activities

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

    business goals and continuity

    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
    辊
    0.48
     Jahrhund
    0.46
     системой
    0.45
     شاعری
    0.43
    ாகு
    0.42
     convencional
    0.42
    க்கார
    0.41
    णाली
    0.41
     انگ
    0.41
     حفظ
    0.41
    POSITIVE LOGITS
     be
    0.54
     replenish
    0.48
     purses
    0.47
    promotion
    0.46
    ]+
    0.45
    ុន
    0.44
    發
    0.43
    ፌ
    0.43
     \{\
    0.43
     ACCESS
    0.42
    Activations Density 0.001%

    No Known Activations