© 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. 188976
    Prev
    Next
    INDEX
    Explanations

    academic paper citations and proceedings

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

    closest to, cheaper than, hope

    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
    ប
    0.45
    ктери
    0.44
     Valves
    0.44
     Ceramic
    0.43
     Bài
    0.42
     Java
    0.42
     Epoxy
    0.41
     Br
    0.41
     valves
    0.41
     teak
    0.41
    POSITIVE LOGITS
    なんて
    0.46
    stru
    0.46
    isdigit
    0.46
    standen
    0.45
     裏
    0.45
     مساعد
    0.44
    sponsored
    0.44
    سون
    0.43
     सख्त
    0.43
     finding
    0.42
    Activations Density 0.000%

    No Known Activations