© 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. 73684
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + first/best/degree/win

    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
    <bos>
    -1.13
    θηκαν
    -1.00
    VIO
    -0.99
     более
    -0.98
    umoj
    -0.97
    gidas
    -0.95
     diámetro
    -0.95
     gastronomía
    -0.95
     സ
    -0.93
    つまり
    -0.93
    POSITIVE LOGITS
     first
    2.28
     own
    1.94
     första
    1.13
     required
    1.12
     ersten
    1.11
     dreamed
    1.11
     longed
    1.11
     bearings
    1.09
     desired
    1.07
    แรก
    1.04
    Activations Density 0.046%

    No Known Activations