© 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. 100299
    Prev
    Next
    INDEX
    Explanations

    financial goals or timelines

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

    describing properties or actions

    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
    줌
    0.51
    ர
    0.47
     እነዚህ
    0.46
    伟大
    0.46
    ंच
    0.44
    надцать
    0.44
    ो
    0.43
    يو
    0.43
    ו
    0.43
    ቹን
    0.43
    POSITIVE LOGITS
     pigmentation
    0.55
     pigment
    0.52
     pigments
    0.49
     genomic
    0.48
     genomics
    0.47
     animations
    0.47
     DAT
    0.47
     statement
    0.44
     microscope
    0.44
    DAT
    0.43
    Activations Density 0.003%

    No Known Activations