© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81846
    Prev
    Next
    INDEX
    Explanations

    formulas and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᴗ
    0.42
     غال
    0.41
     чаще
    0.41
    براير
    0.40
    ารถ
    0.40
    প্রায়
    0.40
    ร
    0.39
    ﻗ
    0.39
     prawd
    0.39
    นี
    0.39
    POSITIVE LOGITS
    pp
    0.48
    lipped
    0.45
     total
    0.42
    総
    0.40
    ere
    0.40
    一片
    0.40
    ールド
    0.40
     ].
    0.40
     tüm
    0.40
    लो
    0.40
    Activations Density 0.017%

    No Known Activations