© 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. 10-GEMMASCOPE-RES-131K
    7. 104949
    Prev
    Next
    INDEX
    Explanations

    postal codes

    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
     about
    -1.98
    }
    -1.75
    ем
    -1.51
     ones
    -1.46
    ERS
    -1.44
    </b>
    -1.42
    nota
    -1.41
    the
    -1.40
    \%)
    -1.39
    nly
    -1.38
    POSITIVE LOGITS
     podríamos
    1.63
     anún
    1.63
     verändert
    1.55
     zowel
    1.51
     drücken
    1.47
     expérimentés
    1.38
    𓏸
    1.38
     Затем
    1.38
     quelques
    1.37
    硖
    1.36
    Activations Density 0.004%

    No Known Activations