© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13960
    Prev
    Next
    INDEX
    Explanations

    collar tighter or higher

    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
    ifiées
    0.98
    thrust
    0.96
    succ
    0.92
    nation
    0.90
    illation
    0.89
    transformed
    0.87
    
    0.86
    ("*
    0.85
    ussion
    0.85
    muştur
    0.84
    POSITIVE LOGITS
     underwhelming
    0.89
     underestimated
    0.87
     escuchar
    0.87
     inclement
    0.86
     teaser
    0.86
     Bailey
    0.86
     shitty
    0.85
     teasing
    0.85
     aunt
    0.83
     Pinterest
    0.83
    Activations Density 0.029%

    No Known Activations