© 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. 34-GEMMASCOPE-RES-131K
    7. 45709
    Prev
    Next
    INDEX
    Explanations

    quoted strings

    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
    With
    -1.12
     SqlDbType
    -1.11
    On
    -1.09
    For
    -1.09
     '*')
    -1.08
    At
    -1.06
     klara
    -1.03
     any
    -1.01
     äls
    -1.00
     bidra
    -0.99
    POSITIVE LOGITS
     "
    2.17
     “
    2.13
     “(
    1.27
     "'
    1.23
    chose
    1.20
    ものに
    1.16
     ‘‘
    1.13
    tells
    1.13
     "$
    1.12
    relatively
    1.11
    Activations Density 0.025%

    No Known Activations