© 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. 15702
    Prev
    Next
    INDEX
    Explanations

    riddle parts: cities, forests, water

    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
     HP
    1.20
     LES
    1.17
     Hp
    1.12
    〗
    1.11
     RES
    1.11
     SJ
    1.10
     Rés
    1.09
     کد
    1.09
    𝑢
    1.07
     Feu
    1.07
    POSITIVE LOGITS
    rawing
    1.16
    rawl
    1.15
    irov
    1.14
    alve
    1.08
    å
    1.07
    election
    1.06
    herald
    1.03
     qīng
    1.03
    orgement
    1.02
     organics
    1.02
    Activations Density 0.001%

    No Known Activations