© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6390
    Prev
    Next
    INDEX
    Explanations

    seeking or offering help and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     orchestration
    1.60
     آه
    1.56
     choreography
    1.56
     choreographed
    1.53
    왜
    1.50
    냠
    1.49
    setAuto
    1.49
     ${{
    1.48
     rematch
    1.47
     rename
    1.44
    POSITIVE LOGITS
    advice
    2.41
     Advice
    2.29
     advice
    2.24
    Advice
    2.11
     advices
    2.07
     advise
    2.05
     conseils
    1.92
     ajudar
    1.83
     advising
    1.81
     Guidance
    1.81
    Activations Density 0.259%

    No Known Activations