© 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. 20829
    Prev
    Next
    INDEX
    Explanations

    states after 'was'

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

    past states and feelings

    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
     নিয়ন্ত্রণে
    0.44
     vet
    0.43
    Predictions
    0.42
     biodegradable
    0.41
     recyclable
    0.41
     revolutionized
    0.40
     diversifying
    0.40
     让
    0.39
    Throwable
    0.39
     discussions
    0.39
    POSITIVE LOGITS
     expecting
    0.51
     esperando
    0.46
    চালক
    0.42
     invitado
    0.40
     Câmara
    0.39
    以為
    0.39
     पूछता
    0.39
     කරයි
    0.39
     bullying
    0.38
     wondering
    0.38
    Activations Density 0.068%

    No Known Activations