© 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. 19872
    Prev
    Next
    INDEX
    Explanations

    Lists of places and assessing relevance

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

    Advanced Tuning and Acquisition

    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
    ем
    0.55
    னி
    0.46
    ұ
    0.45
    collision
    0.45
    આત
    0.45
    创作
    0.44
    ன
    0.44
    но
    0.44
     право
    0.44
    </h3>
    0.43
    POSITIVE LOGITS
     Bestellung
    0.46
     ksi
    0.46
     diminue
    0.46
     আনন্দের
    0.45
     katalog
    0.45
     haus
    0.44
    ্যান্স
    0.43
     dien
    0.42
     picnic
    0.42
     antrop
    0.42
    Activations Density 0.000%

    No Known Activations