© 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. 83095
    Prev
    Next
    INDEX
    Explanations

    uses, those, time, population

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

    safety and policy updates

    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
    ینہ
    0.44
     지원
    0.43
     supporters
    0.42
     supporter
    0.42
    ⬇
    0.40
    ChatMessage
    0.40
    лера
    0.40
    ρική
    0.39
    യാള
    0.39
    惧
    0.39
    POSITIVE LOGITS
     solcher
    0.50
     ちょっと
    0.49
     tohoto
    0.48
    íguez
    0.47
     എന്നതാണ്
    0.46
    adim
    0.46
     KMnO
    0.45
    艙
    0.45
     ريد
    0.44
     něco
    0.44
    Activations Density 0.000%

    No Known Activations