© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12350
    Prev
    Next
    INDEX
    Explanations

    see what we can

    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
     uph
    1.19
     oder
    1.15
    ނ
    1.15
    lemma
    1.13
     eller
    1.12
     smoot
    1.10
    개
    1.08
    ཏ
    1.06
     sieve
    1.05
     arba
    1.05
    POSITIVE LOGITS
     consequently
    1.48
     accordingly
    1.45
    ోంది
    1.43
    その
    1.43
     thereby
    1.42
     thereupon
    1.39
    由此
    1.38
     thereafter
    1.32
    hence
    1.31
     subsequently
    1.29
    Activations Density 0.096%

    No Known Activations