© 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. 59513
    Prev
    Next
    INDEX
    Explanations

    viewing messages

    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
    rever
    -0.88
     actrice
    -0.79
     וְ
    -0.79
    Ɩ
    -0.79
     ponte
    -0.77
    ἄ
    -0.76
     Drill
    -0.74
    larak
    -0.74
     lavable
    -0.74
     merec
    -0.73
    POSITIVE LOGITS
     ¢
    0.84
     quid
    0.77
     GQ
    0.75
     barbie
    0.75
     behe
    0.74
     جامعة
    0.71
     centimetres
    0.70
     Jawahar
    0.70
    )—
    0.69
    lege
    0.69
    Activations Density 0.055%

    No Known Activations