© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2364
    Prev
    Next
    INDEX
    Explanations

    establishment of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     both
    2.44
    unct
    2.21
    囝
    2.18
     organisers
    2.17
     scheme
    2.10
     (‘
    2.10
     historians
    2.10
     either
    2.10
    偕
    2.08
    ouncement
    2.04
    POSITIVE LOGITS
    7
    3.19
    rinsic
    3.11
     subjekt
    3.08
    º
    3.04
    undefined
    2.98
    Diffuse
    2.97
    6
    2.96
    resonant
    2.92
    Entities
    2.87
    tres
    2.86
    Activations Density 0.255%

    No Known Activations