© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2343
    Prev
    Next
    INDEX
    Explanations

    sequences ending with verbs or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     nurses
    1.53
     pneumonia
    1.44
     cardiology
    1.43
    deling
    1.41
     Sox
    1.37
     pandas
    1.35
    맥
    1.34
     dictionaries
    1.34
    肺炎
    1.32
     commas
    1.32
    POSITIVE LOGITS
    7
    1.03
    4
    1.02
    3
    1.00
    6
    0.95
    LICENSE
    0.92
    iptic
    0.92
    prime
    0.92
    iant
    0.90
     permitt
    0.87
    ⅜
    0.85
    Activations Density 0.159%

    No Known Activations