© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    Saudi Arabia, balsamic

    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
    فر
    1.32
     Се
    1.31
    а
    1.30
    افظ
    1.29
    auf
    1.29
    맏
    1.26
    во
    1.25
    ре
    1.24
    yman
    1.23
    ys
    1.19
    POSITIVE LOGITS
     ludicrous
    2.16
     ridiculous
    2.08
     disgraceful
    1.95
     riding
    1.89
     whopping
    1.85
     magnifique
    1.85
     pedestrian
    1.84
     meaningless
    1.84
     noisy
    1.82
     magnificent
    1.81
    Activations Density 0.000%

    No Known Activations