© 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. 109609
    Prev
    Next
    INDEX
    Explanations

    friendship and relationships

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

    real or significant

    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
    ge
    0.52
    A
    0.45
    pkins
    0.43
    than
    0.42
     be
    0.41
    Raj
    0.41
    G
    0.41
    pren
    0.41
    Month
    0.41
    Sof
    0.39
    POSITIVE LOGITS
     médica
    0.50
     médico
    0.49
     lipids
    0.48
     مؤرشف
    0.48
     Médico
    0.46
     religiosa
    0.45
     '*',
    0.45
     alimento
    0.45
     '!
    0.44
     Middleware
    0.44
    Activations Density 0.000%

    No Known Activations