© 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. 221600
    Prev
    Next
    INDEX
    Explanations

    or words following other words

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

    Meme, stereotypes, send, paperwork, arrange fish

    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
    对手
    0.52
    ığınız
    0.50
     بیشتر
    0.47
    sliced
    0.45
     तालिका
    0.45
    opponent
    0.44
    மையாக
    0.44
    ी
    0.43
    дия
    0.42
    Pie
    0.42
    POSITIVE LOGITS
     depots
    0.53
     grits
    0.50
     promot
    0.49
     Transplant
    0.49
     insults
    0.49
     cameras
    0.48
     lotions
    0.47
     promulg
    0.47
     coordinators
    0.47
     xas
    0.46
    Activations Density 0.000%

    No Known Activations