© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    Piloted, tradition, sex, altruism

    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
    off
    2.84
    مس
    2.59
    বারেই
    2.43
    사이
    2.41
    াকুর
    2.39
     mẽ
    2.38
     '**
    2.36
    僱
    2.35
    offs
    2.34
    lap
    2.32
    POSITIVE LOGITS
     vouch
    2.56
     self
    2.35
    ა
    2.28
    iminary
    2.27
    รรม
    2.24
    𝑒
    2.23
    েও
    2.18
    vira
    2.16
    
    2.15
     Self
    2.15
    Activations Density 0.000%

    No Known Activations