© 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. 68715
    Prev
    Next
    INDEX
    Explanations

    call to action

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

    trust, teasing, child

    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
    เป็นการ
    0.54
    ปก
    0.50
    จัดการ
    0.49
    
    0.49
    ช่วย
    0.48
    aniye
    0.46
     செய்யப்படும்
    0.45
    setWalk
    0.44
     अनाउंस
    0.44
    ⊖
    0.44
    POSITIVE LOGITS
     universe
    0.53
     numeros
    0.49
     hit
    0.46
     neuropathy
    0.46
     movement
    0.44
     frustration
    0.44
     Beweg
    0.43
     fractures
    0.43
     gray
    0.43
     port
    0.43
    Activations Density 0.001%

    No Known Activations