© 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. 100836
    Prev
    Next
    INDEX
    Explanations

    apply online application

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

    work and potential

    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
    。,
    0.52
    ꒰
    0.50
    ít
    0.49
    ní
    0.48
    ป์
    0.48
    ětí
    0.46
     ヴィンテージ
    0.46
    ็
    0.45
    ७
    0.45
     meski
    0.45
    POSITIVE LOGITS
     substrates
    0.47
     exer
    0.45
     tanks
    0.44
     strengths
    0.44
     clo
    0.44
     depart
    0.43
     stored
    0.42
     elles
    0.42
    كري
    0.42
     solvers
    0.41
    Activations Density 0.002%

    No Known Activations