© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7280
    Prev
    Next
    INDEX
    Explanations

    samhsa helpline

    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
     shadowing
    0.80
     мъ
    0.78
     към
    0.74
    Depending
    0.73
    ච
    0.70
     deras
    0.69
     στους
    0.69
    &&
    0.68
    мость
    0.68
     deren
    0.68
    POSITIVE LOGITS
     Zweiten
    1.03
     पाता
    1.01
     gesamten
    1.00
     ursprüng
    0.98
     后
    0.98
     Gebiet
    0.95
     humanas
    0.94
     zweiten
    0.92
     einzigen
    0.92
     ersten
    0.92
    Activations Density 0.013%

    No Known Activations