© 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. 12938
    Prev
    Next
    INDEX
    Explanations

    types of, markers of, risk of, stimulation of

    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
    在这个
    -1.15
    ਫ਼
    -1.14
    が行
    -1.13
    キング
    -1.09
     Donegal
    -1.08
    %,
    -1.03
                    
    -1.02
     способствует
    -1.00
    </tbody>
    -0.98
    ></
    -0.96
    POSITIVE LOGITS
     of
    3.31
     on
    1.49
     for
    1.49
     with
    1.38
     at
    1.32
     or
    1.23
     by
    1.20
     to
    1.17
     its
    1.16
     jika
    1.12
    Activations Density 0.078%

    No Known Activations