© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    careful followed by planning or consideration

    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
    𝘢
    2.95
    𝘭
    2.86
    𝘪
    2.69
    𝘦
    2.64
    𝘴
    2.63
    𝘳
    2.57
    ार्ट
    2.56
    𝘵
    2.55
    از
    2.55
    𝘩
    2.55
    POSITIVE LOGITS
     onTap
    2.37
    ore
    2.27
    ׳
    2.26
    ar
    2.24
    toprule
    2.24
    ʇ
    2.16
    carouselExample
    2.16
    鐢
    2.13
     AR
    2.12
     referrerpolicy
    2.05
    Activations Density 0.061%

    No Known Activations