© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107690
    Prev
    Next
    INDEX
    Explanations

    programming code examples

    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_34/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
    нью
    -0.87
    Vill
    -0.82
    werpen
    -0.81
     జ
    -0.77
     אלו
    -0.77
     Politik
    -0.76
    soort
    -0.73
    Lie
    -0.72
    темати
    -0.72
     quem
    -0.71
    POSITIVE LOGITS
    /*
    0.90
    ccini
    0.86
     Redu
    0.86
    };
    0.85
     /*
    0.82
    getResources
    0.82
    umum
    0.81
     including
    0.80
     wakati
    0.79
    };
    
    0.78
    Activations Density 0.018%

    No Known Activations