© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10986
    Prev
    Next
    INDEX
    Explanations

    free tier or plan

    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
     RADIOACTIVE
    2.15
    oluminescence
    2.10
     thermique
    2.07
    ዉ
    2.07
     lézard
    2.01
    terraform
    1.99
    overnment
    1.96
    enf
    1.95
    ev
    1.94
    espace
    1.93
    POSITIVE LOGITS
    ly
    1.96
    ﻊ
    1.53
    te
    1.52
    ʟ
    1.52
    hea
    1.48
    medical
    1.46
    다면
    1.42
    bolic
    1.41
    netics
    1.39
    ᴄ
    1.38
    Activations Density 0.028%

    No Known Activations