© 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. 4361
    Prev
    Next
    INDEX
    Explanations

    here and below

    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
     sabemos
    1.08
     perché
    1.04
     и
    1.02
     और
    0.99
     nostre
    0.97
     এবং
    0.97
     poiché
    0.97
     consideramos
    0.96
     porque
    0.96
     অশ্র
    0.96
    POSITIVE LOGITS
    uje
    1.05
    ometrical
    1.03
    군요
    1.01
    ompact
    0.99
     Abdul
    0.96
    AcOH
    0.96
     @_
    0.95
    Abdul
    0.94
     issuer
    0.94
     '_'
    0.94
    Activations Density 0.130%

    No Known Activations