© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10487
    Prev
    Next
    INDEX
    Explanations

    algoritmos y paths

    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_22_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
    antad
    0.89
     PublicKey
    0.88
     অস্ট্র
    0.88
    キャスト
    0.85
    訂
    0.84
    政府
    0.83
    irmed
    0.81
    ത്തര
    0.81
    emed
    0.81
    𝘋
    0.80
    POSITIVE LOGITS
     technische
    0.93
    터를
    0.91
     technischen
    0.89
     mittels
    0.87
     erhält
    0.87
    욱
    0.87
     Tact
    0.86
    টেড
    0.85
     beating
    0.85
    tica
    0.84
    Activations Density 0.041%

    No Known Activations