© 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. 48057
    Prev
    Next
    INDEX
    Explanations

    years, numbers, percentages, and 'twin'

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

    actions or states described

    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
    ]
    0.52
    0
    0.47
    ge
    0.44
     tuck
    0.44
    ho
    0.44
    developed
    0.44
    has
    0.43
    umy
    0.43
    6
    0.43
    ])
    0.43
    POSITIVE LOGITS
     REACTOR
    0.50
    鋐
    0.48
     प्रश्नों
    0.45
    ⌔
    0.44
    數量
    0.44
    耖
    0.43
     சம்பவ
    0.43
     দেখিয়
    0.43
     వాటి
    0.42
    лябин
    0.42
    Activations Density 0.001%

    No Known Activations