© 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. 385
    Prev
    Next
    INDEX
    Explanations

    Who is

    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
    Coll
    1.55
    Parl
    1.51
    ੁਰ
    1.51
     bulunur
    1.46
    ਧ
    1.43
     Parl
    1.42
    Acc
    1.42
    Ste
    1.41
    Dios
    1.41
    Hearts
    1.39
    POSITIVE LOGITS
     adjudication
    1.39
    iswa
    1.39
    脍
    1.38
     norms
    1.33
    apeutics
    1.33
     PPAR
    1.31
    itability
    1.29
    藻
    1.27
     AEC
    1.26
     primarily
    1.25
    Activations Density 0.000%

    No Known Activations