© 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. 22-GEMMASCOPE-RES-131K
    4. 12785
    Prev
    Next
    INDEX
    Explanations

    listing items after parentheses and for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ???:
    -1.44
    🤑
    -1.42
    🥱
    -1.39
     sista
    -1.37
    🗿
    -1.34
    செ
    -1.30
    🤏
    -1.29
     pittores
    -1.28
    😠
    -1.28
     fuf
    -1.27
    POSITIVE LOGITS
     this
    1.98
     use
    1.66
     maybe
    1.62
     especially
    1.59
     including
    1.58
     leave
    1.56
     they
    1.55
     same
    1.53
     result
    1.53
     also
    1.52
    Activations Density 0.034%

    No Known Activations