© 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. 11451
    Prev
    Next
    INDEX
    Explanations

    phone number models

    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
    盹
    1.68
    albeit
    1.65
    anthin
    1.60
     bootstrapping
    1.59
    撸
    1.58
     cursory
    1.57
    émon
    1.55
    fileobj
    1.54
    umbling
    1.53
     ônibus
    1.53
    POSITIVE LOGITS
     зимо
    1.11
     растений
    1.01
    J
    1.01
     pas
    0.99
    A
    0.98
     tega
    0.98
    DRA
    0.98
    NA
    0.97
    ปรุง
    0.97
     ,,
    0.96
    Activations Density 0.231%

    No Known Activations