© 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. 34-GEMMASCOPE-RES-131K
    4. 116106
    Prev
    Next
    INDEX
    Explanations

    debug, Gul, Current, This, UPDATE

    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_34/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
     their
    -1.39
     sehr
    -1.23
     that
    -1.11
     unrelenting
    -1.09
     Very
    -1.09
     Unlike
    -1.06
     get
    -1.05
     out
    -1.05
     or
    -1.04
     collaborative
    -1.04
    POSITIVE LOGITS
     –
    1.55
     -
    1.12
     $-$
    1.08
    rician
    1.05
    }-\
    1.04
     EASY
    1.01
     Univer
    1.01
     blessés
    1.00
     -\
    1.00
     —
    0.99
    Activations Density 0.000%

    No Known Activations