© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    recursion and algorithmic inefficiency

    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
     kennt
    1.27
     zrozum
    1.13
    を見て
    1.11
    signale
    1.10
     막
    1.10
    riko
    1.10
     widers
    1.08
     웃
    1.07
    景观
    1.04
    谚
    1.02
    POSITIVE LOGITS
     impending
    1.18
     pending
    1.02
     imminent
    0.97
     deposit
    0.95
     full
    0.93
     batches
    0.92
     batch
    0.91
     battery
    0.90
     depósito
    0.89
    assem
    0.86
    Activations Density 0.319%

    No Known Activations