© 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. 14614
    Prev
    Next
    INDEX
    Explanations

    find a therapist

    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
    itens
    1.06
     *_
    1.03
     planned
    1.02
     encouraged
    0.98
     suggested
    0.96
     illustrated
    0.95
     Heading
    0.95
     nomenclature
    0.95
     সফ
    0.93
    illustrated
    0.93
    POSITIVE LOGITS
    rą
    1.02
    ᐉ
    0.97
    ęb
    0.96
     elusive
    0.93
    ől
    0.91
    玲
    0.87
    сом
    0.85
     debajo
    0.85
    ńskim
    0.85
     Robb
    0.85
    Activations Density 0.292%

    No Known Activations