© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7478
    Prev
    Next
    INDEX
    Explanations

    crisis helpline numbers

    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_22_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
    лата
    1.07
     apie
    0.98
     about
    0.95
     Acerca
    0.91
    ستی
    0.90
    約
    0.90
    about
    0.90
     respecto
    0.89
     عنها
    0.88
    约
    0.88
    POSITIVE LOGITS
     midway
    1.59
     halfway
    1.50
     equidistant
    1.46
    Guess
    1.13
     midpoint
    1.11
    ToExp
    1.09
     mid
    1.08
     midrange
    1.07
    Version
    1.05
     evenly
    1.03
    Activations Density 0.100%

    No Known Activations