© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141741
    Prev
    Next
    INDEX
    Explanations

    dominating, rhythm, lost, seekers, Political

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

    narrow winding streets

    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_31_width_262k_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
    OffsetY
    0.56
    Timestamp
    0.46
    BeforeCall
    0.46
    et
    0.46
    anay
    0.45
    uesthouse
    0.45
    anu
    0.45
     津
    0.45
     samu
    0.44
    curities
    0.44
    POSITIVE LOGITS
     UNION
    0.51
     биографи
    0.48
     nanot
    0.47
     maxx
    0.47
     customizations
    0.47
     minimized
    0.46
    ını
    0.45
     всем
    0.45
    !);
    0.45
    𝗩
    0.45
    Activations Density 0.000%

    No Known Activations