© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104486
    Prev
    Next
    INDEX
    Explanations

    condensation **of** liquid

    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
     greateſt
    -2.53
     合金
    -2.39
    饧
    -2.38
    please
    -2.36
     diversos
    -2.33
    osoba
    -2.31
     myriad
    -2.31
    锨
    -2.20
     Pristup
    -2.20
     broader
    -2.19
    POSITIVE LOGITS
    ↵
    3.64
    \
    2.55
    ’
    2.47
    他们是
    2.44
     WITH
    2.23
    </h2>
    2.14
    鸯
    2.11
    with
    2.09
    E
    2.09
    </sup>
    2.08
    Activations Density 0.012%

    No Known Activations