© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 45353
    Prev
    Next
    INDEX
    Explanations

    city names as datelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UL
    0.47
    க்கூ
    0.41
    PARAM
    0.41
    COMPILE
    0.40
    through
    0.39
     Arbor
    0.39
     U
    0.38
     ORDIN
    0.38
     CAPACITY
    0.38
     grandchildren
    0.38
    POSITIVE LOGITS
    ťa
    0.47
    ..?
    0.47
    Provence
    0.45
    :'',
    0.45
     witty
    0.44
    🤟
    0.44
     disob
    0.44
    דו
    0.44
    ática
    0.43
    یتے
    0.43
    Activations Density 0.001%

    No Known Activations