© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148245
    Prev
    Next
    INDEX
    Explanations

    identification and purpose

    np_acts-logits-general · gemini-2.5-flash-lite

    multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     byla
    0.54
    }$.
    0.49
    に取り
    0.49
     byly
    0.48
     were
    0.48
     waren
    0.46
     были
    0.46
     sont
    0.46
    が必要です
    0.45
     furono
    0.45
    POSITIVE LOGITS
     ettiği
    0.54
    的那
    0.46
    怎樣
    0.43
    彥
    0.42
    በት
    0.42
     गरेको
    0.42
     কোথায়
    0.41
     केलेल्या
    0.41
    duğu
    0.41
     Areas
    0.40
    Activations Density 0.005%

    No Known Activations