© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201604
    Prev
    Next
    INDEX
    Explanations

    trained on a massive dataset including

    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_31_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
     two
    0.38
    ERGY
    0.36
     benefits
    0.36
    नोट
    0.36
    ائے
    0.35
     дві
    0.35
    ர
    0.35
     paed
    0.35
     বঞ্চিত
    0.35
    㳻
    0.35
    POSITIVE LOGITS
     опор
    0.48
     sayıda
    0.45
    uitse
    0.45
    fake
    0.44
    കേന്ദ്രം
    0.43
    simulate
    0.43
    நிதி
    0.43
    support
    0.42
    anglement
    0.42
    ennzeichnet
    0.42
    Activations Density 0.007%

    No Known Activations