© 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. 75993
    Prev
    Next
    INDEX
    Explanations

    identifying authors or sources

    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
     parlamento
    -0.96
    likace
    -0.93
     médic
    -0.93
     població
    -0.93
    灵气
    -0.92
     tahun
    -0.91
    ppich
    -0.90
     indien
    -0.90
    сный
    -0.89
    ﻹ
    -0.89
    POSITIVE LOGITS
     admin
    1.30
    admin
    1.22
     says
    1.05
     Pingback
    1.02
     sagt
    1.00
    (";
    0.98
     pisze
    0.96
     می‌گو
    0.94
    ~"
    0.91
     Matt
    0.89
    Activations Density 0.009%

    No Known Activations