© 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. 7573
    Prev
    Next
    INDEX
    Explanations

    section headings and introductions

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

    section headers

    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
     certainement
    0.38
    福音
    0.37
     لگتا
    0.36
     huit
    0.36
    giờ
    0.36
     নিশ্চয়
    0.36
    糬
    0.35
     दृष्टि
    0.35
    ពេលវេល
    0.35
    鉗
    0.35
    POSITIVE LOGITS
    </h2>
    0.71
    简介
    0.42
    ούν
    0.41
     அறிமுக
    0.41
    ⤒
    0.41
     verw
    0.40
    definition
    0.38
    ünde
    0.38
    ℠
    0.38
     waarmee
    0.38
    Activations Density 0.000%

    No Known Activations