© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5589
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    :
    1.35
    culis
    1.26
    :(
    1.19
    egin
    1.19
    lah
    1.17
    ousy
    1.14
    、「
    1.14
    ībā
    1.14
    ´
    1.14
    oyl
    1.14
    POSITIVE LOGITS
    <eos>
    2.19
     This
    2.08
     While
    2.02
     These
    2.00
     What
    1.98
     Ultimately
    1.93
     """)
    1.89
     However
    1.88
     Despite
    1.88
    <h2>
    1.87
    Activations Density 0.598%

    No Known Activations