© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70915
    Prev
    Next
    INDEX
    Explanations

    divided, then cemented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -2.13
     inſ
    -1.58
     extremadamente
    -1.55
     meskipun
    -1.51
     göm
    -1.50
    ჻
    -1.47
     сейчас
    -1.43
    ſo
    -1.42
    っていますが
    -1.42
     musíte
    -1.41
    POSITIVE LOGITS
     was
    1.77
     during
    1.74
     by
    1.74
     with
    1.55
     IActionResult
    1.47
     at
    1.41
     while
    1.38
     насеља
    1.36
     when
    1.36
     on
    1.36
    Activations Density 0.027%

    No Known Activations