© 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. 206754
    Prev
    Next
    INDEX
    Explanations

    cultural references, granite guarantee, your team

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

    Laplace transforms and inherent properties

    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
    を示
    0.49
    гле
    0.45
     interactions
    0.44
    член
    0.43
    Viewer
    0.42
    CHREIB
    0.42
    PROOF
    0.42
    釗
    0.41
    цый
    0.40
    িয়াস
    0.40
    POSITIVE LOGITS
     फेमस
    0.43
    der
    0.42
     Camden
    0.41
     Lately
    0.41
     Workmen
    0.40
    ecommerce
    0.40
    strftime
    0.40
     lately
    0.40
    dır
    0.40
     Nashville
    0.40
    Activations Density 0.000%

    No Known Activations