© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57859
    Prev
    Next
    INDEX
    Explanations

    package com

    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
     kabát
    -1.17
    
    -1.13
    tarta
    -1.13
     ternyata
    -1.12
     kampus
    -1.11
    série
    -1.11
     vrijdag
    -1.11
    】:
    -1.10
     jadwal
    -1.09
    getMenuInflater
    -1.09
    POSITIVE LOGITS
    java
    1.12
    w
    1.05
    "
    1.05
    j
    1.05
    he
    1.03
    —
    1.02
    ab
    1.02
    ap
    1.01
    y
    1.00
    **
    0.98
    Activations Density 0.062%

    No Known Activations