© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    for loop index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schade
    2.30
    resist
    2.16
     macht
    2.04
     nhớ
    2.00
     machen
    1.91
     stof
    1.91
    偻
    1.89
    𝚑
    1.86
    סי
    1.86
    ﻑ
    1.86
    POSITIVE LOGITS
    nable
    1.86
    mM
    1.83
    winfo
    1.80
    ujjati
    1.76
    kada
    1.76
     agrarian
    1.75
    bedkar
    1.75
    tio
    1.74
     IIT
    1.73
    irectional
    1.73
    Activations Density 0.008%

    No Known Activations