© 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. 183475
    Prev
    Next
    INDEX
    Explanations

    specific contexts and classifications

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

    design, iteration, specific features

    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
     vän
    0.50
    湎
    0.50
     fortiter
    0.48
     settore
    0.47
     patham
    0.46
     vég
    0.46
    živ
    0.46
    ✍
    0.46
    👬
    0.44
    ärg
    0.44
    POSITIVE LOGITS
    ズ
    0.49
    Class
    0.47
    Fitz
    0.47
     conversely
    0.46
     deleted
    0.46
    TED
    0.46
     Fitzgerald
    0.46
    Ireland
    0.45
     provided
    0.45
    ]").
    0.44
    Activations Density 0.000%

    No Known Activations