© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    technical concepts and dependencies

    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
    <0xF3>
    1.59
    diox
    1.49
    𓏧
    1.49
    |.|.|
    1.43
     Griffiths
    1.43
     궁
    1.41
    沮
    1.40
    ᵔ
    1.39
    throat
    1.38
     Hogg
    1.37
    POSITIVE LOGITS
     रहेको
    1.06
     Rena
    1.05
    //
    1.00
     данного
    0.98
    e
    0.94
    also
    0.92
    के
    0.92
    помним
    0.91
    ذلك
    0.91
        
    0.90
    Activations Density 3.061%

    No Known Activations