© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10413
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines 988 741

    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_22_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
    ndal
    1.05
     اع
    1.04
    LOGIN
    0.98
    瞳
    0.96
    nda
    0.96
    grep
    0.96
     Determ
    0.93
    nykh
    0.93
     Secretario
    0.90
     عضو
    0.90
    POSITIVE LOGITS
    ight
    0.82
    =
    0.82
    計
    0.82
     lasting
    0.82
     économique
    0.81
     durée
    0.80
     price
    0.79
     marché
    0.78
     multiplied
    0.77
     compar
    0.77
    Activations Density 0.004%

    No Known Activations