© 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. 100761
    Prev
    Next
    INDEX
    Explanations

    communication and appearance

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

    cooling, refreshing, 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
    трі
    0.49
    scopic
    0.45
    ధిక
    0.45
    п
    0.45
    пе
    0.44
    ந்துக
    0.44
     ಇದನ್ನು
    0.43
    𝘰
    0.42
    ᱖
    0.42
     stk
    0.40
    POSITIVE LOGITS
     pollinators
    0.49
    ao
    0.46
     ব্রিগে
    0.44
     chargés
    0.43
    Martin
    0.43
    യാ
    0.42
     pollin
    0.42
     المل
    0.42
     dependents
    0.41
     lidí
    0.41
    Activations Density 0.000%

    No Known Activations