© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71095
    Prev
    Next
    INDEX
    Explanations

    case reports

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

    citation references in academic papers, particularly those using brackets and numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    檍
    -2.42
    櫚
    -2.41
    ...........
    -2.30
     The
    -2.20
     ($("#
    -2.19
    崀
    -2.17
     nella
    -2.13
     folgende
    -2.09
    ">“
    -2.08
     visant
    -2.08
    POSITIVE LOGITS
    z
    2.36
    as
    2.33
    ’,
    2.30
    تهى
    2.19
     místě
    2.17
     Also
    2.16
    ⢮
    2.14
    ಿ
    2.08
     incredible
    2.05
    時の
    2.02
    Activations Density 0.019%

    No Known Activations