© 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. 3752
    Prev
    Next
    INDEX
    Explanations

    Cold War

    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
     delikat
    2.27
    yse
    2.22
    geordnet
    2.21
    ዛት
    2.20
    ekan
    2.19
    usement
    2.17
    اعری
    2.15
    娀
    2.12
    írás
    2.08
    radical
    2.08
    POSITIVE LOGITS
     מד
    2.05
     רו
    2.00
     fi
    2.00
     ຈ
    1.89
    ో
    1.85
    ளையும்
    1.85
     Dead
    1.84
    ือง
    1.82
     nowhere
    1.81
     הרו
    1.81
    Activations Density 0.000%

    No Known Activations