© 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. 48194
    Prev
    Next
    INDEX
    Explanations

    README file

    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
    }
    -2.80
    ]
    -2.69
     Hinblick
    -2.36
    1
    -2.16
     Bedürfn
    -2.13
     you
    -2.06
     {
    -2.06
     }
    -2.02
     We
    -2.02
    "
    -1.99
    POSITIVE LOGITS
    勠
    2.38
    别人的
    2.34
    勦
    2.30
     itſelf
    2.25
    sandalia
    2.19
     friv
    2.17
    ⒍
    2.14
    絎
    2.09
    櫺
    2.08
    
    2.06
    Activations Density 0.013%

    No Known Activations