© 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. 105839
    Prev
    Next
    INDEX
    Explanations

    recent articles or sales

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

    Caesar cipher shift and injection attacks

    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
     長財布
    0.47
     grandeur
    0.47
     గొప్ప
    0.47
    ዥ
    0.46
    ಿಸಿದರು
    0.46
    ждает
    0.46
     Fiore
    0.46
     अन्याय
    0.46
    ArchivePath
    0.46
     искусство
    0.45
    POSITIVE LOGITS
    如果
    0.43
    给定
    0.42
    溪
    0.42
     appropriate
    0.42
    加
    0.41
    明天
    0.40
     bra
    0.40
     Acting
    0.40
    サム
    0.40
    '
    0.40
    Activations Density 0.001%

    No Known Activations