© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132514
    Prev
    Next
    INDEX
    Explanations

    Understanding

    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_40_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
    Rocket
    0.48
    stufe
    0.43
    CMI
    0.39
    cow
    0.39
    Für
    0.39
    ऽ
    0.39
    JI
    0.38
    III
    0.38
    src
    0.38
    Locked
    0.38
    POSITIVE LOGITS
     النهايات
    0.45
     QuantityOnHand
    0.44
     emocional
    0.43
     gay
    0.42
     scenarios
    0.41
    টিভ
    0.40
     ovulation
    0.40
     وین
    0.40
     girly
    0.40
    悅
    0.39
    Activations Density 0.001%

    No Known Activations