© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    LoRA, Loong, So

    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
    了
    4.87
    nya
    4.55
    ly
    4.35
    اً
    4.09
    نام
    3.89
    います
    3.84
    서
    3.53
    ting
    3.50
    r
    3.45
    다고
    3.31
    POSITIVE LOGITS
    ে
    4.71
    <bos>
    4.15
    ğlu
    4.07
    ה
    3.91
    es
    3.81
    ه
    3.71
    pportun
    3.63
    an
    3.54
    oos
    3.48
    a
    3.43
    Activations Density 0.492%

    No Known Activations