© 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. 153767
    Prev
    Next
    INDEX
    Explanations

    making a move

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

    conjunctions and descriptions

    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
    al
    0.65
    als
    0.63
     I
    0.56
    ata
    0.56
    ed
    0.52
    3
    0.51
    ar
    0.50
    erm
    0.49
    å
    0.49
    we
    0.48
    POSITIVE LOGITS
     egyszerű
    0.60
     étamines
    0.54
     stockno
    0.54
     einfache
    0.53
     astron
    0.52
     améliorer
    0.50
     enzim
    0.50
     trasform
    0.50
    жному
    0.49
     gemakkelijk
    0.49
    Activations Density 0.002%

    No Known Activations