© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3270
    Prev
    Next
    INDEX
    Explanations

    "to" followed by actions

    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
    s
    3.94
    ات
    3.06
    sle
    3.06
    াপনের
    3.00
    sley
    2.99
    sia
    2.88
    Accelerator
    2.85
    <div>
    2.81
    saga
    2.75
    sack
    2.75
    POSITIVE LOGITS
    বীন্দ্র
    2.80
    shid
    2.65
    िलायंस
    2.60
    𝐧
    2.58
    home
    2.55
    дона
    2.51
    िश्वत
    2.51
    सायनिक
    2.48
    ých
    2.42
    𝗻
    2.39
    Activations Density 0.069%

    No Known Activations