© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4709
    Prev
    Next
    INDEX
    Explanations

    quoted text boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     гео
    0.90
     tek
    0.88
    魚
    0.87
     dodgy
    0.87
    楶
    0.87
     tzv
    0.87
     bogus
    0.86
    显
    0.86
     promote
    0.85
    各种
    0.85
    POSITIVE LOGITS
    ிடம்
    0.64
    ?"
    0.56
    ?”
    0.55
    ரிடம்
    0.54
    "?
    0.52
    naires
    0.51
    œil
    0.50
    ":
    0.49
     osim
    0.48
    нице
    0.48
    Activations Density 0.211%

    No Known Activations