© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11871
    Prev
    Next
    INDEX
    Explanations

    given names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite

    person's name followed by relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OutgoingRiver
    0.48
     折り
    0.47
     girly
    0.45
    sq
    0.44
     MILK
    0.44
    这种
    0.44
     乳
    0.44
    squarePos
    0.43
    垭
    0.43
    そういう
    0.43
    POSITIVE LOGITS
    spouse
    0.40
    hausen
    0.38
     Ehe
    0.38
     (
    0.37
    Lives
    0.37
    published
    0.36
     (†
    0.36
     spouse
    0.36
     Lives
    0.34
     sucedido
    0.34
    Activations Density 0.048%

    No Known Activations