© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41035
    Prev
    Next
    INDEX
    Explanations

    years with hyphenated dates

    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
    titial
    -2.41
    鹛
    -1.91
     and
    -1.84
    vitational
    -1.78
    鹀
    -1.73
    ceptable
    -1.72
    骘
    -1.70
    颔
    -1.69
    經常
    -1.61
    complish
    -1.57
    POSITIVE LOGITS
    也
    2.08
    ↵
    2.06
    1
    2.05
    2
    2.02
     endeavor
    1.79
    ]
    1.78
    on
    1.76
    轳
    1.72
    ～」
    1.64
    は
    1.63
    Activations Density 0.041%

    No Known Activations