© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57766
    Prev
    Next
    INDEX
    Explanations

    delivering promises, quality, or results

    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
     foray
    -1.11
     endeavors
    -1.06
     ทุก
    -1.05
     Ее
    -1.04
    各样的
    -1.04
    来越
    -1.03
    wość
    -1.02
    טה
    -1.01
     большого
    -1.01
     endeavours
    -1.00
    POSITIVE LOGITS
     to
    2.13
     on
    1.80
     delivers
    1.72
     what
    1.68
     delivered
    1.57
     delivering
    1.55
     deliver
    1.53
     Deliver
    1.45
     unto
    1.42
     upon
    1.27
    Activations Density 0.026%

    No Known Activations