© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6839
    Prev
    Next
    INDEX
    Explanations

    states of absence or past events

    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
     cheeky
    1.65
    Initially
    1.63
    Vegan
    1.58
    Delicious
    1.57
    Nowadays
    1.53
    ⁂
    1.52
    🩷
    1.52
    ⬤
    1.50
    Emoji
    1.48
    Ultimately
    1.48
    POSITIVE LOGITS
     skall
    1.26
     standpoint
    1.09
     shall
    1.01
     uh
    0.99
     ,
    0.99
     defense
    0.96
     되었
    0.95
     superintend
    0.94
     defenses
    0.93
    膛
    0.92
    Activations Density 0.030%

    No Known Activations