© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5267
    Prev
    Next
    INDEX
    Explanations

    energy, protest, academics

    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
     synthesis
    1.38
     rese
    1.16
    फिल्म
    1.15
    ர்
    1.12
     esa
    1.10
     Struct
    1.09
    鮫
    1.08
     ak
    1.07
     ler
    1.07
    اده
    1.06
    POSITIVE LOGITS
    vislosti
    1.40
    ⒏
    1.35
    <bos>
    1.34
     GameOver
    1.31
    のでは
    1.28
    VERTISE
    1.28
     Nagy
    1.27
    jid
    1.27
    匐
    1.26
    smtb
    1.25
    Activations Density 0.000%

    No Known Activations