© 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. 92836
    Prev
    Next
    INDEX
    Explanations

    code snippets with php

    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
     disseminate
    -0.74
     Vikram
    -0.71
    Mash
    -0.69
    verbatim
    -0.68
    ibm
    -0.68
    TIM
    -0.68
    ason
    -0.66
     כל
    -0.65
     consum
    -0.65
     enigma
    -0.65
    POSITIVE LOGITS
    episode
    0.70
    MouseUp
    0.68
     Fru
    0.64
     paus
    0.63
    itemList
    0.63
    AWARDS
    0.63
     trato
    0.62
     Obst
    0.62
    ꯩ
    0.61
     mampu
    0.61
    Activations Density 0.054%

    No Known Activations