© 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. 240
    Prev
    Next
    INDEX
    Explanations

    strings and diverse vocabulary

    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
    3
    1.21
    6
    1.20
    week
    1.19
    year
    1.13
    8
    1.09
    ople
    1.08
     st
    1.08
    4
    1.05
    9
    1.04
    5
    1.03
    POSITIVE LOGITS
    ᡧ
    1.89
    ர்களும்
    1.81
     러
    1.79
     FIC
    1.76
     방식
    1.73
     자유
    1.72
    侓
    1.72
     な
    1.71
     далі
    1.70
     Ната
    1.69
    Activations Density 0.000%

    No Known Activations