© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94348
    Prev
    Next
    INDEX
    Explanations

    organization funds contact

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

    no resolution or breakthrough

    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
    Negative Logits
    strom
    0.44
    娃娃
    0.43
    wechsl
    0.43
    iguing
    0.42
    abul
    0.42
    guns
    0.41
    时
    0.40
    埆
    0.40
    strates
    0.39
    ated
    0.39
    POSITIVE LOGITS
     всіх
    0.48
     arah
    0.45
    ণির
    0.44
     całym
    0.43
     inzwischen
    0.42
     "--
    0.42
    ᑖ
    0.42
     wcex
    0.42
     wszystkie
    0.42
    </code>
    0.41
    Activations Density 0.001%

    No Known Activations