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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5830
    Prev
    Next
    INDEX
    Explanations

    technical aspects for specific audiences

    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
    
    2.27
    utches
    2.26
    苞
    2.21
    adilla
    2.10
    urahan
    2.10
    skich
    2.07
    )&&
    2.07
     قدر
    2.04
    롤
    1.98
    ysuckle
    1.96
    POSITIVE LOGITS
    यंस
    2.45
    㵴
    2.44
    ian
    2.24
    weile
    2.24
     admirable
    2.23
    generation
    2.22
     हेलो
    2.21
     Pickering
    2.20
    crm
    2.20
    iaire
    2.19
    Activations Density 0.930%

    No Known Activations