© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15604
    Prev
    Next
    INDEX
    Explanations

    REST API and pandas

    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_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
     injurious
    0.91
    治
    0.84
     deleterious
    0.83
     necessitated
    0.82
    ,]
    0.81
     poison
    0.80
     lead
    0.80
    წყვე
    0.79
    ],
    0.79
     fundamentally
    0.78
    POSITIVE LOGITS
     презен
    1.28
    iqui
    1.24
    Markers
    1.22
    attes
    1.21
    cyon
    1.21
     मेहमान
    1.20
     mał
    1.20
    itipi
    1.19
    eward
    1.18
    osterol
    1.17
    Activations Density 0.000%

    No Known Activations