© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by delimiters

    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
    us
    1.82
    ”
    1.63
    mind
    1.62
    un
    1.57
     tale
    1.56
    consciousness
    1.53
    pit
    1.53
    ic
    1.51
    pa
    1.50
     interrupt
    1.43
    POSITIVE LOGITS
    andfeel
    2.84
    硞
    2.70
    驒
    2.69
    覦
    2.68
    armafit
    2.67
     gstlal
    2.67
    𒄐
    2.65
     იყ
    2.64
    EYER
    2.59
    𐰑
    2.59
    Activations Density 0.088%

    No Known Activations