© 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. 168176
    Prev
    Next
    INDEX
    Explanations

    month experience

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

    sustainability, brand, significant, actual, box

    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
    掏
    0.48
     complied
    0.46
    ità
    0.45
    等等
    0.45
    高雄
    0.44
    在本
    0.44
     isso
    0.44
    跑
    0.43
    掩
    0.43
    椿
    0.43
    POSITIVE LOGITS
    acles
    0.47
    unities
    0.46
     بیٹے
    0.46
    em
    0.46
     वाले
    0.46
    inel
    0.46
    ни
    0.45
    angels
    0.45
     center
    0.45
     funders
    0.45
    Activations Density 0.000%

    No Known Activations