© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57448
    Prev
    Next
    INDEX
    Explanations

    lenses that

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

    feel lonely, remember, stopped

    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
     Ведь
    0.47
     lenguaje
    0.44
     observables
    0.43
     hombres
    0.43
     subgroups
    0.43
     vec
    0.42
    ﮑ
    0.42
     Б
    0.41
     Profits
    0.41
     accion
    0.40
    POSITIVE LOGITS
    edere
    0.52
    xiety
    0.52
    ipe
    0.50
    okie
    0.50
    owane
    0.49
    eonium
    0.48
    ulas
    0.48
    etic
    0.48
    anne
    0.48
    ienka
    0.47
    Activations Density 0.000%

    No Known Activations