© 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. 221651
    Prev
    Next
    INDEX
    Explanations

    phrases of word plus common follower

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

    specialize

    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
     resonance
    0.44
     comport
    0.44
    ীন
    0.43
     WR
    0.42
     connecting
    0.41
     ș
    0.41
     certification
    0.41
     explained
    0.41
     coefficient
    0.41
     competed
    0.41
    POSITIVE LOGITS
    NV
    0.49
    existent
    0.49
    ani
    0.48
    CHES
    0.46
    {|\
    0.46
    砳
    0.46
    全部
    0.46
    éb
    0.45
    ffmpeg
    0.45
    expiry
    0.45
    Activations Density 0.001%

    No Known Activations