© 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. 37854
    Prev
    Next
    INDEX
    Explanations

    Native claims and rights

    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
    mois
    -0.81
    щення
    -0.80
    енная
    -0.77
    ()};
    -0.76
    hdessä
    -0.74
     immédi
    -0.74
    roffen
    -0.73
    chaine
    -0.71
     ję
    -0.71
    енный
    -0.71
    POSITIVE LOGITS
     claim
    1.32
     claims
    1.31
     Claims
    1.23
    Claim
    1.20
     Claim
    1.16
    claim
    1.10
    claims
    1.09
     rights
    1.08
     land
    1.07
     CLAIM
    1.03
    Activations Density 0.015%

    No Known Activations