© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2109
    Prev
    Next
    INDEX
    Explanations

    World War

    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
    .
    0.84
    6
    0.72
     historic
    0.65
     historical
    0.65
    2
    0.64
    @
    0.63
    0.62
    4
    0.59
    3
    0.59
     #
    0.58
    POSITIVE LOGITS
    Able
    1.56
    ampu
    1.53
     ajustable
    1.53
     inputRange
    1.51
    отно
    1.50
     allowNull
    1.50
     сможет
    1.49
     אפ
    1.44
     Able
    1.44
     MHK
    1.43
    Activations Density 0.479%

    No Known Activations