© 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. 30573
    Prev
    Next
    INDEX
    Explanations

    exclamation mark

    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
    debit
    -0.76
    Instru
    -0.68
    ear
    -0.68
    ถือ
    -0.67
    桡
    -0.67
     IELTS
    -0.66
    貴重な
    -0.66
    するための
    -0.66
    nyt
    -0.64
    isance
    -0.64
    POSITIVE LOGITS
     exclamation
    4.41
     exclaimed
    3.61
     exc
    3.58
     exclaim
    3.30
    exc
    3.30
     Exc
    3.22
    Exc
    2.86
     exclaims
    2.84
     воск
    2.69
     excl
    2.02
    Activations Density 0.076%

    No Known Activations