© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    protected void methods

    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
     élus
    -0.95
    parently
    -0.95
     marea
    -0.94
    φορά
    -0.94
     investis
    -0.91
    ᠡ
    -0.88
     gelatina
    -0.88
     desbloquear
    -0.88
     igreja
    -0.88
    んですよね
    -0.88
    POSITIVE LOGITS
     void
    1.69
    void
    1.44
     from
    1.05
     int
    1.02
     dia
    0.86
     Tor
    0.85
     BUT
    0.85
     PLUS
    0.85
     PD
    0.85
     async
    0.84
    Activations Density 0.002%

    No Known Activations