© 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. 68662
    Prev
    Next
    INDEX
    Explanations

    names and places followed by verbs

    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
     just
    -1.15
    ;
    -1.14
     when
    -1.14
     from
    -1.04
    :
    -1.03
     time
    -1.02
     at
    -1.02
     an
    -1.01
     "..\..\
    -1.01
     any
    -1.00
    POSITIVE LOGITS
     was
    1.55
     will
    1.33
    はこの
    1.31
     is
    1.30
    
    1.22
     lanterna
    1.20
    ఝ
    1.19
     resistente
    1.18
     multicolore
    1.15
     faciliter
    1.13
    Activations Density 0.126%

    No Known Activations