© 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. 89703
    Prev
    Next
    INDEX
    Explanations

    help you get creative

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

    stronger more impactful words

    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
    Ľ
    0.50
    ￥
    0.50
     Fools
    0.47
    ‑
    0.46
     Liet
    0.45
     Honestly
    0.44
     Leer
    0.44
     Lichten
    0.43
    ‐
    0.43
     Loth
    0.43
    POSITIVE LOGITS
    ج
    0.56
    MyDB
    0.53
     पुढील
    0.47
    شون
    0.46
    保养
    0.44
    uzten
    0.44
    ंपूर्
    0.43
     autoradi
    0.42
    ڈیو
    0.42
    VertexBuffer
    0.42
    Activations Density 0.000%

    No Known Activations