© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31932
    Prev
    Next
    INDEX
    Explanations

    I have been

    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
     still
    -1.45
    ेशा
    -1.40
    歘
    -1.17
     not
    -1.16
    农场
    -1.15
     libere
    -1.11
     cardíaca
    -1.09
    enskap
    -1.08
     dotyczy
    -1.08
     pozwala
    -1.07
    POSITIVE LOGITS
     to
    2.22
     told
    1.62
     meaning
    1.50
     through
    1.41
    meaning
    1.38
     able
    1.23
     into
    1.17
     involved
    1.16
     in
    1.14
     warned
    1.09
    Activations Density 0.029%

    No Known Activations