© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12652
    Prev
    Next
    INDEX
    Explanations

    don't blame yourself

    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
    ࢮ
    2.73
     validInput
    2.66
    ㄼ
    2.49
    fico
    2.46
    apaccay
    2.44
     setTo
    2.34
    ेक्ट
    2.34
    eris
    2.33
     imgSrc
    2.30
    INGO
    2.28
    POSITIVE LOGITS
    డు
    1.96
    সু
    1.60
    stone
    1.57
    data
    1.56
    anı
    1.51
    た
    1.48
     ins
    1.48
     devices
    1.48
    仕組み
    1.46
    راک
    1.45
    Activations Density 0.051%

    No Known Activations