© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    depends on context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    にて
    1.44
    そこに
    1.31
    )。
    1.26
    。...
    1.26
     ذریعے
    1.25
    即可
    1.25
     +.
    1.25
     होकर
    1.24
    が
    1.24
    。
    1.22
    POSITIVE LOGITS
     depends
    2.83
     varies
    2.56
    depends
    2.27
     depende
    2.27
     varía
    2.26
     depend
    2.14
     bergantung
    2.08
     vary
    2.08
     depended
    2.04
     depender
    2.03
    Activations Density 0.454%

    No Known Activations