© 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. 133974
    Prev
    Next
    INDEX
    Explanations

    action verbs and nouns

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

    Facebook country Temporary Stay insurance

    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
     ट्रैक्टर
    0.51
     검색
    0.51
    𝚟
    0.48
     évaluations
    0.48
    용한
    0.48
    恐惧
    0.47
    終わ
    0.47
    ɰ
    0.46
    মধ্যেই
    0.46
    ꞎ
    0.46
    POSITIVE LOGITS
    ↵
    0.51
    *.
    0.46
    asp
    0.45
    ৪০
    0.45
    layers
    0.45
    কুল
    0.44
    ৬০
    0.42
    ink
    0.41
     গৃহ
    0.40
    .</
    0.40
    Activations Density 0.001%

    No Known Activations