© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2549
    Prev
    Next
    INDEX
    Explanations

    let me know or let's

    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_7_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
    дук
    2.94
    iatrics
    2.81
    कौन
    2.71
    ITY
    2.68
    ি
    2.58
     biskup
    2.56
    undai
    2.55
     nga
    2.55
     कराने
    2.49
    ">—
    2.47
    POSITIVE LOGITS
    tering
    2.50
    ramp
    2.41
    ting
    2.41
    ching
    2.30
    ல்லிய
    2.29
    ras
    2.22
    ymology
    2.20
    aney
    2.20
    鐢
    2.18
    </ul>
    2.13
    Activations Density 0.088%

    No Known Activations