© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 9348
    Prev
    Next
    INDEX
    Explanations

    HTML line breaks and tags

    np_acts-logits-general · gemini-2.5-flash-lite

    paragraph tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    ==(
    0.41
     administ
    0.41
     AML
    0.38
     Eliza
    0.37
    McL
    0.37
    !\!\
    0.37
    ==
    0.36
    [:]
    0.36
    !=
    0.36
    ะไร
    0.36
    POSITIVE LOGITS
    "{@
    0.58
    {@
    0.55
     {@
    0.55
     思い
    0.41
    </ul>
    0.40
    ;<
    0.39
    𝖑
    0.39
    <0xF2>
    0.38
     Васи
    0.37
    ophagus
    0.37
    Activations Density 0.007%

    No Known Activations