© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 793
    Prev
    Next
    INDEX
    Explanations

    sentences and words

    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
     noble
    1.17
     સુ
    1.15
     incur
    1.14
     فر
    1.12
     subdued
    1.12
     Ư
    1.11
     испол
    1.06
     acquies
    1.06
     בש
    1.06
     monog
    1.06
    POSITIVE LOGITS
    otek
    1.20
    ormal
    1.19
    ikam
    1.19
    ignez
    1.15
    Sb
    1.14
    ulte
    1.11
    olt
    1.10
    oder
    1.08
    ％
    1.08
    okat
    1.07
    Activations Density 0.370%

    No Known Activations