© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    extra mile or despair

    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
    autom
    1.81
    esses
    1.80
    ahkan
    1.54
    zetac
    1.51
    मर्रा
    1.49
    bolos
    1.48
    浾
    1.46
    icions
    1.45
    eren
    1.41
    ungkinkan
    1.41
    POSITIVE LOGITS
     价
    1.58
     Люди
    1.53
     קר
    1.48
     Celebration
    1.48
     童
    1.47
    ­
    1.47
     꿈
    1.47
     哦
    1.44
     Celebrate
    1.44
     ねえ
    1.42
    Activations Density 0.011%

    No Known Activations