© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8627
    Prev
    Next
    INDEX
    Explanations

    launch from Kennedy, checking information

    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
    इसी
    1.30
    živ
    1.21
    ផង
    1.15
    ž
    1.14
    ALT
    1.08
     रजिस्ट
    1.07
    жным
    1.06
    č
    1.06
    أل
    1.06
    ăr
    1.06
    POSITIVE LOGITS
    ക്ക്
    0.93
     হতে
    0.90
     spherical
    0.90
     scratch
    0.88
     intractable
    0.88
     susceptibility
    0.87
     IX
    0.84
     interessa
    0.83
     expedited
    0.83
     complex
    0.81
    Activations Density 0.000%

    No Known Activations