© 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. 238645
    Prev
    Next
    INDEX
    Explanations

    organization categories

    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
    Mar
    0.53
    `);
    0.50
     Isle
    0.47
    mar
    0.45
    lang
    0.45
     Marines
    0.44
     Mari
    0.42
     Decatur
    0.41
     orn
    0.41
    WebContent
    0.41
    POSITIVE LOGITS
     ajud
    0.54
    των
    0.50
    ικοί
    0.49
    helps
    0.49
    竄
    0.49
    ੨
    0.48
    怎样的
    0.47
     помога
    0.47
    痙
    0.47
    ოთ
    0.47
    Activations Density 0.001%

    No Known Activations