© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    fictional characters and combat

    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
     Việt
    1.76
    ographiques
    1.65
     /(\
    1.63
     গত
    1.61
     UBND
    1.58
    ographique
    1.57
     Ủy
    1.56
     (>
    1.53
     বাংলাদেশ
    1.53
     નવી
    1.52
    POSITIVE LOGITS
     angrily
    1.78
     glared
    1.72
     enraged
    1.69
     hatred
    1.68
     muttered
    1.66
     undead
    1.65
     nodded
    1.63
     knights
    1.62
     summoned
    1.59
     chuckled
    1.59
    Activations Density 0.747%

    No Known Activations