© 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. 13135
    Prev
    Next
    INDEX
    Explanations

    end of html body

    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
    y
    2.31
    ed
    2.14
    garten
    2.10
    wort
    2.07
    थमिक
    2.06
     appears
    2.06
    र
    2.02
    कारात्मक
    2.01
    ctomy
    2.01
     lay
    1.96
    POSITIVE LOGITS
    𝘬
    3.11
    ControlType
    3.03
    searchDisplay
    2.89
    koord
    2.86
    sberg
    2.75
    ataires
    2.71
    RefCount
    2.65
    范围内
    2.62
    oksatta
    2.62
     norme
    2.60
    Activations Density 0.006%

    No Known Activations