© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    foundation or core components

    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_13_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
     heartbeat
    1.01
    ppure
    0.95
     poke
    0.93
     petal
    0.92
    িপূর্ণ
    0.92
     vertex
    0.91
    ﹕
    0.90
     berry
    0.87
     dawn
    0.87
    ነት
    0.87
    POSITIVE LOGITS
    i
    0.96
    al
    0.85
    als
    0.82
    approximately
    0.74
    Lands
    0.73
    care
    0.73
    Only
    0.71
     मात्रा
    0.71
    len
    0.70
     amounts
    0.70
    Activations Density 0.120%

    No Known Activations