© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31477
    Prev
    Next
    INDEX
    Explanations

    historical and descriptive details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fen
    0.38
    aptic
    0.36
     swam
    0.36
     PDEs
    0.36
    𓂃
    0.36
     Ln
    0.36
     assumed
    0.34
     Presentation
    0.34
     Fen
    0.34
     Xe
    0.34
    POSITIVE LOGITS
    emote
    0.43
     człowie
    0.42
    ListIterator
    0.38
     Seeger
    0.37
    ͟
    0.37
    gebnis
    0.37
     মেয়ের
    0.37
     emuls
    0.36
    silhouette
    0.36
    //////////////
    0.36
    Activations Density 0.001%

    No Known Activations