© 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. 249471
    Prev
    Next
    INDEX
    Explanations

    design intent, have more, tuition, 7, NSW, all rights, know that, beautiful staircase

    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
    ρικ
    0.49
    蓄
    0.45
    间隔
    0.44
    लभ
    0.44
    лькі
    0.43
    тли
    0.43
    ї
    0.43
    𝕠
    0.41
    ڑک
    0.41
     milhões
    0.41
    POSITIVE LOGITS
     Aut
    0.55
    ne
    0.55
     Prés
    0.54
     AN
    0.54
     aut
    0.52
     Georgia
    0.52
    2
    0.52
     Nan
    0.52
     Ma
    0.52
     singer
    0.52
    Activations Density 0.000%

    No Known Activations