© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3116
    Prev
    Next
    INDEX
    Explanations

    float declarations with keywords

    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
    泹
    1.94
     samma
    1.92
     hetzelfde
    1.89
     gleichen
    1.87
     même
    1.86
    䋇
    1.86
    knię
    1.83
     dezelfde
    1.83
     mismas
    1.82
    籿
    1.81
    POSITIVE LOGITS
     arrowhead
    1.61
     demands
    1.56
     award
    1.52
    arte
    1.52
     arrows
    1.52
     arrow
    1.51
     envoy
    1.47
    лын
    1.45
     proposals
    1.44
     was
    1.44
    Activations Density 0.004%

    No Known Activations