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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11711
    Prev
    Next
    INDEX
    Explanations

    number followed by security or colon

    np_acts-logits-general · gemini-2.5-flash-lite

    instruction, goals, hash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    1
    0.46
    $=
    0.45
    Covid
    0.43
     sixth
    0.39
    *:
    0.38
    *(
    0.38
    Laws
    0.38
    Lemma
    0.37
    MONTH
    0.37
    泊
    0.37
    POSITIVE LOGITS
    ″
    0.72
    ′
    0.71
    ′,
    0.51
    ️⃣
    0.46
     ″
    0.45
     BABY
    0.44
    ″]
    0.43
     oligonucleotide
    0.42
    ⃣
    0.41
    だし
    0.41
    Activations Density 0.575%

    No Known Activations