© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1095
    Prev
    Next
    INDEX
    Explanations

    path, address, equations

    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
     relevant
    0.86
     WOR
    0.84
     arts
    0.84
     living
    0.83
     mental
    0.83
     giving
    0.82
    :
    0.80
     teaching
    0.80
    ,
    0.80
    EX
    0.79
    POSITIVE LOGITS
    ścic
    1.23
     Sekunden
    1.19
     Jeżeli
    1.16
     toneladas
    1.15
    сматри
    1.13
    皓
    1.13
    <unused866>
    1.13
    ικο
    1.11
     خمسه
    1.09
    ählte
    1.09
    Activations Density 0.114%

    No Known Activations