© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51681
    Prev
    Next
    INDEX
    Explanations

    mass-energy equivalence

    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_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
    j
    0.44
     J
    0.42
    belt
    0.41
     policies
    0.40
    atam
    0.40
     j
    0.40
    us
    0.39
    policy
    0.39
    z
    0.38
    wire
    0.38
    POSITIVE LOGITS
     Nucleaire
    0.48
    粒子
    0.44
    弋
    0.44
     తిరిగి
    0.43
    腖
    0.43
     నిర్మాత
    0.42
    нце
    0.41
    NUCLEAR
    0.41
    ᠰ
    0.41
     APIDC
    0.41
    Activations Density 0.007%

    No Known Activations