© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65398
    Prev
    Next
    INDEX
    Explanations

    said reports and quotes

    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
    Nella
    -1.18
    Abbiamo
    -1.16
    丁目
    -1.16
    ፑ
    -1.16
     viewWillAppear
    -1.09
    トマト
    -1.09
    größern
    -1.08
     we
    -1.07
    ─
    -1.05
     disponibilités
    -1.03
    POSITIVE LOGITS
     said
    1.56
     zima
    1.26
     Евгений
    1.09
    いてる
    1.06
     from
    1.05
     told
    1.05
     both
    1.02
     okt
    1.02
     сказал
    1.00
    emeni
    0.98
    Activations Density 0.018%

    No Known Activations