© 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. 9220
    Prev
    Next
    INDEX
    Explanations

    location builder

    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
     wa
    0.95
     non
    0.95
     divers
    0.94
    圍
    0.88
    資源
    0.87
     not
    0.87
     augment
    0.86
     waste
    0.84
    divers
    0.84
    var
    0.84
    POSITIVE LOGITS
    sframe
    1.23
     jednostavno
    1.22
    sgem
    1.20
    datac
    1.17
    ⇝
    1.17
     Macaulay
    1.16
    ➩
    1.16
     adata
    1.15
     Mudah
    1.15
     datasheet
    1.13
    Activations Density 0.010%

    No Known Activations