© 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. 57719
    Prev
    Next
    INDEX
    Explanations

    comparison or quantity followed by noun

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

    save her

    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
     церкви
    0.52
    結晶
    0.52
    コム
    0.51
    レクト
    0.51
    ргә
    0.49
    合った
    0.49
    フルーツ
    0.49
    礫
    0.49
    忶
    0.49
    рог
    0.48
    POSITIVE LOGITS
     city
    0.54
    ikke
    0.52
     Bad
    0.51
     yang
    0.51
    spring
    0.50
    ella
    0.50
     saate
    0.50
    state
    0.49
    aa
    0.49
    ene
    0.49
    Activations Density 0.000%

    No Known Activations