© 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. 36098
    Prev
    Next
    INDEX
    Explanations

    code logic with return

    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
    providedIn
    -1.40
     by
    -1.26
    嫆
    -1.16
     __
    -1.16
     communiquez
    -1.15
     cyclisme
    -1.13
    ሖ
    -1.13
     δὲ
    -1.10
     onlyOwner
    -1.08
    ㈠
    -1.08
    POSITIVE LOGITS
    ’
    1.30
    O
    1.10
     sommige
    1.09
    无疑
    1.08
    _
    1.07
     aanzien
    1.06
     renegade
    1.05
    判斷
    1.05
     calcu
    1.03
     aanz
    1.03
    Activations Density 0.001%

    No Known Activations