© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19726
    Prev
    Next
    INDEX
    Explanations

    lease, contract, abandonment

    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_31_width_262k_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
     ವರ್ಷ
    0.51
     увла
    0.50
     нагре
    0.50
    ক্স
    0.50
     inactivació
    0.49
     manne
    0.48
     黒
    0.47
     bhij
    0.47
     gacche
    0.47
     заряд
    0.46
    POSITIVE LOGITS
     Contracts
    0.53
    Contract
    0.45
     Contract
    0.44
    i
    0.44
    arios
    0.43
    orkan
    0.43
    apour
    0.42
    ܫ
    0.42
    Contracts
    0.42
     contracts
    0.42
    Activations Density 0.000%

    No Known Activations