© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8926
    Prev
    Next
    INDEX
    Explanations

    time spent, management, pressure, travel

    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
    idding
    2.49
    голо
    2.23
    rien
    2.17
    idded
    2.16
    aisseur
    2.14
    نى
    2.14
    SIE
    2.06
    ن
    2.06
    ന്നും
    2.04
    ल
    2.03
    POSITIVE LOGITS
     बिता
    3.06
     Comptroller
    2.55
     $>$
    2.52
    frames
    2.52
     spent
    2.42
    г
    2.32
     permiso
    2.32
     foragers
    2.30
    Pods
    2.29
    chn
    2.26
    Activations Density 0.277%

    No Known Activations