© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 658
    Prev
    Next
    INDEX
    Explanations

    wanting help during struggle

    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_13_width_65k_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
     unnecessary
    1.78
     overly
    1.70
     finely
    1.62
    <unused46>
    1.61
     burdensome
    1.59
     sophisticated
    1.58
     particles
    1.57
     vertebrae
    1.56
     cumbersome
    1.56
    <unused1252>
    1.55
    POSITIVE LOGITS
    1
    1.45
    0
    1.45
     giugno
    1.36
    9
    1.33
    6
    1.31
    2
    1.29
    3
    1.25
    7
    1.23
     octubre
    1.22
     luglio
    1.20
    Activations Density 0.672%

    No Known Activations