© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1052
    Prev
    Next
    INDEX
    Explanations

    memorability and solar

    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
    inj
    1.53
    infested
    1.52
    5
    1.52
    loads
    1.49
    iny
    1.45
    burst
    1.43
    f
    1.43
    relief
    1.42
    4
    1.42
    7
    1.37
    POSITIVE LOGITS
    <unused1985>
    2.09
     Aaj
    1.84
     columnIndex
    1.83
     CHI
    1.82
     ナイ
    1.81
     Gradient
    1.79
     ISE
    1.76
     Ribe
    1.75
    ｜
    1.75
     海
    1.74
    Activations Density 0.028%

    No Known Activations