© 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. 10-GEMMASCOPE-RES-131K
    7. 80845
    Prev
    Next
    INDEX
    Explanations

    variable v

    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_10/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
    #%%
    -1.53
     begleitet
    -1.52
     your
    -1.50
    唢
    -1.45
     You
    -1.44
    然后
    -1.43
    欵
    -1.41
    llavero
    -1.40
    广州
    -1.39
    VICT
    -1.39
    POSITIVE LOGITS
     nossos
    1.85
     começar
    1.65
     crescer
    1.63
     ajudar
    1.58
    を見つけ
    1.53
    ネイル
    1.53
    狛
    1.52
     ficar
    1.52
    rament
    1.49
    ごめん
    1.49
    Activations Density 0.028%

    No Known Activations