© 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
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1534
    Prev
    Next
    INDEX
    Explanations

    leaving behind or unattended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     centered
    1.04
     erat
    1.01
    鵠
    0.91
     clap
    0.89
    꽤
    0.88
    act
    0.88
    Reference
    0.88
     sand
    0.87
     практику
    0.87
    ந்துக
    0.87
    POSITIVE LOGITS
     endowments
    1.20
     room
    1.20
    [{{
    1.15
    ⓤ
    1.14
     rooms
    1.14
     unattended
    1.13
     indelible
    1.11
    inn
    1.11
    ⋘
    1.09
     presumption
    1.08
    Activations Density 0.088%

    No Known Activations