© 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. 60770
    Prev
    Next
    INDEX
    Explanations

    hotels and hostels

    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
    </b>
    -2.16
     its
    -1.79
    </em>
    -1.73
    它的
    -1.63
    Its
    -1.60
    </td>
    -1.36
     jetzt
    -1.34
    </h4>
    -1.33
    -1.30
     l
    -1.30
    POSITIVE LOGITS
    /***
    1.32
     zwem
    1.30
     Escribe
    1.25
     eerst
    1.23
    の様子
    1.22
    ⅓
    1.22
     schrij
    1.21
     vroeg
    1.19
    ಲ್ಲಿ
    1.18
    CHANT
    1.17
    Activations Density 0.023%

    No Known Activations