© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14138
    Prev
    Next
    INDEX
    Explanations

    parts of compound words

    np_acts-logits-general · gemini-2.5-flash-lite

    Company names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ydney
    0.45
    FC
    0.44
    I
    0.42
    <0x81>
    0.41
    ัญ
    0.39
    email
    0.39
    AV
    0.37
    cosystem
    0.37
    ќ
    0.37
    are
    0.36
    POSITIVE LOGITS
     covariant
    0.41
     Noetherian
    0.40
     incriminating
    0.40
     JUnit
    0.40
     ListNode
    0.39
     DIC
    0.38
     destruction
    0.38
     Betracht
    0.38
     Dynkin
    0.38
     Nauchno
    0.38
    Activations Density 0.074%

    No Known Activations