Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3937
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     variously
    1.19
    াবলী
    1.19
     courte
    1.13
    Matched
    1.10
    Ӏ
    1.08
     undertake
    1.07
     concatenate
    1.07
     microtub
    1.06
     barre
    1.05
     meanwhile
    1.05
    POSITIVE LOGITS
    ási
    1.26
    *.
    1.25
    》。
    1.17
    isant
    1.14
    .*
    1.14
    يين
    1.12
    GroupBy
    1.11
    ശാസ്ത്ര
    1.10
    годи
    1.10
    。
    1.10
    Activations Density 0.114%

    No Known Activations