© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58776
    Prev
    Next
    INDEX
    Explanations

    Source Electronic Components investmentgamification customerscrowdfunding investmentinternship positionsPEOs

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

    importance of specific terms

    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_262k_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
    .',
    0.48
    .
    0.48
    ',
    0.46
     configuring
    0.46
     Raised
    0.45
     Activate
    0.45
     Lockdown
    0.45
     Connect
    0.43
     Taking
    0.43
     içerisinde
    0.43
    POSITIVE LOGITS
     遊ん
    0.47
     Америки
    0.46
     अमेरिका
    0.46
     聞い
    0.46
     స్వాధీ
    0.46
     書い
    0.45
    égek
    0.45
     받
    0.44
     やっ
    0.43
     계획
    0.43
    Activations Density 0.001%

    No Known Activations