© 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. 34-GEMMASCOPE-RES-131K
    7. 38128
    Prev
    Next
    INDEX
    Explanations

    | delimiter

    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_34/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
    )()
    -0.68
    #%%
    -0.68
    كاتب
    -0.68
    山中
    -0.68
    }{}
    -0.67
    cameras
    -0.66
    مصادر
    -0.66
     cameras
    -0.66
     шли
    -0.65
    ذر
    -0.65
    POSITIVE LOGITS
     |
    4.66
    |
    3.89
     $|
    3.63
     $|\
    3.28
     |
    2.81
    ∣
    2.75
    ｜
    2.73
     '|
    2.67
     "|
    2.66
    |\
    2.58
    Activations Density 0.375%

    No Known Activations