© 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. 136477
    Prev
    Next
    INDEX
    Explanations

    sensitive to

    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
     l
    0.50
     الآ
    0.49
     dit
    0.46
    Телефон
    0.44
    দ্দা
    0.43
    ଳ
    0.43
    ام
    0.43
    ات
    0.42
    أم
    0.41
     telefon
    0.41
    POSITIVE LOGITS
    칩
    0.46
     ashore
    0.43
     elucid
    0.43
    ishable
    0.43
     முருக
    0.41
    étés
    0.41
     This
    0.41
    thisobject
    0.41
     rubble
    0.41
    machen
    0.41
    Activations Density 0.001%

    No Known Activations